THE CONSCIOUSNESS ATLAS
Read. Experiment. Follow the evidence.
Every recovered mathematical record has an individual page. Browse original equations, code expressions, indexed components, parameter definitions, and explicitly unresolved source slots.
Counts refer to mathematical records, including implemented expressions and generated instances. They are not counts of independently validated theories. Exact occurrences and unresolved slots remain traceable. Read the complete 1–516 source index ↗ · Inspect the scan decisions ↗
In DeepseekV3Attention.forward, this statement defines or updates attn_weights. Softmax exponentiates and normalizes scores along the chosen axis, producing nonnegative weights that sum to one when inputs are finite. The matrix or indexed contraction combines the stated axes. Compatible tensor…
In DeepseekV3Attention.forward, this statement defines or updates attn_weights. The addition or subtraction updates the named state or combines residual contributions. The input shapes and the order in the surrounding forward path must be preserved.
In DeepseekV3Attention.forward, this statement defines or updates q. This statement evaluates the named projection, normalization or numeric transform with the source arguments. Its learned parameters and exact input shape are defined by the surrounding module.
In DeepseekV3Attention.forward, this statement defines or updates q. This statement evaluates the named projection, normalization or numeric transform with the source arguments. Its learned parameters and exact input shape are defined by the surrounding module.
In DeepseekV3DecoderLayer.__init__, this statement defines or updates self.mlp. This statement evaluates the named projection, normalization or numeric transform with the source arguments. Its learned parameters and exact input shape are defined by the surrounding module.
In DeepseekV3DynamicNTKScalingRotaryEmbedding._set_cos_sin_cache, this statement defines or updates base. The expression forms a quotient or integer division. The denominator, integer rounding and tensor shape convention determine its scale or index result.
In DeepseekV3DynamicNTKScalingRotaryEmbedding._set_cos_sin_cache, this statement defines or updates inv_freq. This is part of the positional-phase calculation. Frequency, position, sine/cosine and coordinate ordering must agree with the source rotary convention.
In DeepseekV3FlashAttention2._upad_input, this statement defines or updates cu_seqlens_q. The addition or subtraction updates the named state or combines residual contributions. The input shapes and the order in the surrounding forward path must be preserved.
In DeepseekV3FlashAttention2._upad_input, this statement defines or updates key_layer. The displayed multiplication combines the source factors. For tensors this is elementwise unless the called operation explicitly performs a matrix contraction.
In DeepseekV3FlashAttention2._upad_input, this statement defines or updates max_seqlen_in_batch_q. This statement fixes a numeric parameter or initializes a numerical state in this source version; it is not a separate governing law.
In DeepseekV3FlashAttention2._upad_input, this statement defines or updates query_layer. The displayed multiplication combines the source factors. For tensors this is elementwise unless the called operation explicitly performs a matrix contraction.
In DeepseekV3FlashAttention2._upad_input, this statement defines or updates value_layer. The displayed multiplication combines the source factors. For tensors this is elementwise unless the called operation explicitly performs a matrix contraction.
In DeepseekV3FlashAttention2.forward, this statement defines or updates attn_output. The displayed multiplication combines the source factors. For tensors this is elementwise unless the called operation explicitly performs a matrix contraction.
In DeepseekV3ForSequenceClassification.forward, this statement defines or updates output. The addition or subtraction updates the named state or combines residual contributions. The input shapes and the order in the surrounding forward path must be preserved.
In DeepseekV3ForSequenceClassification.forward, this statement defines or updates pooled_logits. This statement evaluates the named projection, normalization or numeric transform with the source arguments. Its learned parameters and exact input shape are defined by the surrounding module.
In DeepseekV3ForSequenceClassification.forward, this statement returns the displayed result. The addition or subtraction updates the named state or combines residual contributions. The input shapes and the order in the surrounding forward path must be preserved.
In DeepseekV3ForSequenceClassification.forward, this statement defines or updates sequence_lengths. The addition or subtraction updates the named state or combines residual contributions. The input shapes and the order in the surrounding forward path must be preserved.
In DeepseekV3LinearScalingRotaryEmbedding._set_cos_sin_cache, this statement defines or updates freqs. This is part of the positional-phase calculation. Frequency, position, sine/cosine and coordinate ordering must agree with the source rotary convention.
In DeepseekV3LinearScalingRotaryEmbedding._set_cos_sin_cache, this statement defines or updates t. The expression forms a quotient or integer division. The denominator, integer rounding and tensor shape convention determine its scale or index result.
In DeepseekV3MoE.__init__, this statement defines or updates self.experts. The displayed multiplication combines the source factors. For tensors this is elementwise unless the called operation explicitly performs a matrix contraction.
In DeepseekV3MoE.__init__, this statement defines or updates self.experts_per_rank. The expression forms a quotient or integer division. The denominator, integer rounding and tensor shape convention determine its scale or index result.
In DeepseekV3MoE.__init__, this statement defines or updates intermediate_size. The displayed multiplication combines the source factors. For tensors this is elementwise unless the called operation explicitly performs a matrix contraction.
In DeepseekV3MoE.moe_infer, this statement defines or updates end_idx. The addition or subtraction updates the named state or combines residual contributions. The input shapes and the order in the surrounding forward path must be preserved.
In DeepseekV3MoE.moe_infer, this statement defines or updates expert. The displayed multiplication combines the source factors. For tensors this is elementwise unless the called operation explicitly performs a matrix contraction.
In DeepseekV3MoE.moe_infer, this statement defines or updates gatherd_idxs[s:s + k]. This statement evaluates the named projection, normalization or numeric transform with the source arguments. Its learned parameters and exact input shape are defined by the surrounding module.
In DeepseekV3MoE.moe_infer, this statement defines or updates gathered_tokens. The reduction aggregates values along the explicit source axis; preserving the axis and keep-dimension setting matters for the later broadcast.
In DeepseekV3MoE.moe_infer, this statement defines or updates output_splits. The reduction aggregates values along the explicit source axis; preserving the axis and keep-dimension setting matters for the later broadcast.
In DeepseekV3MoE.moe_infer, this statement defines or updates sorted_tokens. The top-k operation selects the largest scores. Ties and group masking affect which experts or entries survive the discrete boundary.
In DeepseekV3MoE.moe_infer, this statement defines or updates tokens_per_ep_rank. The reduction aggregates values along the explicit source axis; preserving the axis and keep-dimension setting matters for the later broadcast.
In DeepseekV3MoE.moe_infer, this statement defines or updates tokens_per_expert. The reduction aggregates values along the explicit source axis; preserving the axis and keep-dimension setting matters for the later broadcast.
In DeepseekV3MoE.moe_infer, this statement defines or updates tokens_per_expert_post_gather. The reduction aggregates values along the explicit source axis; preserving the axis and keep-dimension setting matters for the later broadcast.
In DeepseekV3Model.forward, this statement defines or updates hidden_states. This statement evaluates the named projection, normalization or numeric transform with the source arguments. Its learned parameters and exact input shape are defined by the surrounding module.
In DeepseekV3Model.forward, this statement defines or updates past_key_values_length. This statement fixes a numeric parameter or initializes a numerical state in this source version; it is not a separate governing law.
In DeepseekV3Model.forward, this statement defines or updates position_ids. The addition or subtraction updates the named state or combines residual contributions. The input shapes and the order in the surrounding forward path must be preserved.
In DeepseekV3RotaryEmbedding.__init__, this statement defines or updates inv_freq. This is part of the positional-phase calculation. Frequency, position, sine/cosine and coordinate ordering must agree with the source rotary convention.
In DeepseekV3RotaryEmbedding._set_cos_sin_cache, this statement defines or updates freqs. This is part of the positional-phase calculation. Frequency, position, sine/cosine and coordinate ordering must agree with the source rotary convention.
In DeepseekV3RotaryEmbedding._set_cos_sin_cache, this statement defines or updates t. This is part of the positional-phase calculation. Frequency, position, sine/cosine and coordinate ordering must agree with the source rotary convention.
In DeepseekV3YarnRotaryEmbedding._set_cos_sin_cache, this statement defines or updates freq_extra. The expression forms a quotient or integer division. The denominator, integer rounding and tensor shape convention determine its scale or index result.
In DeepseekV3YarnRotaryEmbedding._set_cos_sin_cache, this statement defines or updates freq_inter. The expression forms a quotient or integer division. The denominator, integer rounding and tensor shape convention determine its scale or index result.
In DeepseekV3YarnRotaryEmbedding._set_cos_sin_cache, this statement defines or updates freqs. This is part of the positional-phase calculation. Frequency, position, sine/cosine and coordinate ordering must agree with the source rotary convention.
In DeepseekV3YarnRotaryEmbedding._set_cos_sin_cache, this statement defines or updates t. This statement evaluates the named projection, normalization or numeric transform with the source arguments. Its learned parameters and exact input shape are defined by the surrounding module.
In KimiK25ForConditionalGeneration._merge_input_ids_with_image_features, this statement defines or updates final_embedding[batch_indices, indices_to_mask]. This statement fixes a numeric parameter or initializes a numerical state in this source version; it is not a separate governing law.
In KimiK25ForConditionalGeneration._merge_input_ids_with_image_features, this statement defines or updates image_to_overwrite. The addition or subtraction updates the named state or combines residual contributions. The input shapes and the order in the surrounding forward path must be preserved.
In KimiK25ForConditionalGeneration._merge_input_ids_with_image_features, this statement defines or updates left_padding. The reduction aggregates values along the explicit source axis; preserving the axis and keep-dimension setting matters for the later broadcast.
In KimiK25ForConditionalGeneration._merge_input_ids_with_image_features, this statement defines or updates max_embed_dim. The reduction aggregates values along the explicit source axis; preserving the axis and keep-dimension setting matters for the later broadcast.
In KimiK25ForConditionalGeneration._merge_input_ids_with_image_features, this statement defines or updates nb_image_pad. The addition or subtraction updates the named state or combines residual contributions. The input shapes and the order in the surrounding forward path must be preserved.