NeurIPS 2026 reviews are up: reviews, scores, rebuttals and meta-reviews for 7,877 papers. See the highest rated
acceptodds: the papers of ICLR 2027
689 results for “keyword:"mechanistic interpretability"” in ICLR 2027. 142 withdrawn or desk rejected listed apart. clearsort:relevanceratingnewestmost read
[PDF]Can a One-Layer Transformer Solve Hard Sudoku? Test-Time Compute, Generalization, and Mechanistic Analysis▼4.5k2.67
[PDF]fDAG-ACDC: Uncertainty-Adaptive Factor-Count Selection for High-Dimensional Causal Discovery▲1.5k3.50
[PDF]Subliminal Learning Through Mechanism Reuse: How Models Can Transmit Hidden Traits In Unrelated Data▼2443.33
[PDF]How Optimality Structures Sparse Dictionaries: Theory for Interpreting SAE Representations▲5.4k3.00
[PDF]Skill Co-activation Graphs: A Functional Topology of Generalization in Large Language Models▼4.3k2.00
[PDF]How Vision Transformers Represent Position: A Mechanistic Comparison of Absolute and Rotary Positional Encodings▲3.0k2.33
[PDF]When Does Depth Matter For In-Context Learning? Adaptive Inference in Deep Transformers▼1.2k3.00
[PDF]Transformers develop separable posterior and value representations in a simple decision task▼4.3k2.00
[PDF]Emergent Codon Frame Representations Reveal Mechanisms of Translation in Genomic Foundation Models▲143.33
[PDF]Encoding Without Alignment: Analyzing The Correspondence Between LLMs And The Visual Cortex▼1.2k1.67
[PDF]The Arithmetic Error Bar: A First-Passage Law for the Numerical Fragility of Language Models▼1361.33
[PDF]Interventional Commutativity: Effect Preservation and Reference Selection Under Weight-Only Quantisation▼1.2k1.67
[PDF]Readable Constraints, Unreliable Decisions: A Constraint-Instantiation Lens on Language Model Errors▼1361.33
[PDF]Conditional Backdoors Leave Traces in J-Space of Code-Generating Large Language Models▼1.2k1.67
[PDF]Gradients for Interventions and Activations for Detection: Targeted Feature Learning in Language Models▼4.3k2.00
[PDF]A Geometric View for Understanding Concept Learning and Neuron Interpretation in Sparse Autoencoders▲5.4k3.00
[PDF]Multi-Dimensional Featurizers Yield Fine-Grained Steering and Data Shaping in Robot Foundation Models▼5.1k2.60
[PDF]MixCoder: Decomposing Neural Computation into Low-Rank Transformations over Low-Dimensional Representations▼4.3k2.00
Withdrawn or desk rejected (142)
[PDF]Why Benign Post-Training Induces Safety Gate Collapse: Changes in Harmful Activation Geometry Relative to the Inherited Refusal GateWithdrawn1.67
[PDF]Concept Subspaces Compute Beyond the Logit Lens: A Weights-Only Test for Locating Representations Upstream of ReadoutWithdrawn