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
729 results for “keyword:"mechanistic"” in ICLR 2027. 152 withdrawn or desk rejected listed apart. clearsort:relevanceratingnewestmost read
[PDF]Shared Weights, Selected Computations: How Looped Transformers Route What Each Loop Does▼4.3k2.00
[PDF]SAE-Locked LoRA: Edit-Specific Sparse-Feature Gradient Routing for Low-Interference Knowledge Editing▼4.5k2.67
[PDF]WorldModelLens: From Attention to Rollouts - A framework for World Model Interpretability▼4.3k2.00
[PDF]When Can Agents Forget Their Reasoning? ICLR for Long-Horizon Agent Context Compression▲3.0k2.33
[PDF]What the Nonnegative Lens Misses: Energy-Matched Causal Tests of the J-Space in Open Language Models▲11.00
[PDF]Sensitivity Before Connectivity: Minimal Pairs Reveal How CNNs Learn a Global Visual Rule▼4.3k2.00
[PDF]MoE Routing Is Not Token-Local: How Expert Influence Propagates Across Tokens & Layers▼4.5k2.67
[PDF]Written as a Record, Read as an Address: What a Forward Pass Leaves in an Operation's KV Cache▲3.0k2.33
[PDF]QuTab: A Single Mutable-State Transformer for Mechanistically Interpretable Tabular In-Context Learning▼1.2k3.00
[PDF]From Input to Output: A Flexible Agent for Dual-End Interpretation of Sparse Autoencoder Features▲9.2k2.67
[PDF]Where Massive Activations Come From: Causal Evidence from MLP Geometry in Large Language Models▲3952.67
[PDF]Bidirectional Causal Tracing and Intervention: Causal Mechanism-Guided Machine Unlearning▼4.3k2.00
[PDF]Beyond the Commitment Boundary: Probing Epiphenomenal Chain-of-Thought in Large Reasoning Models▼1.2k1.67
[PDF]From Spectral Responses to Task Effects: Auditing Frequency Dependence in Spiking Neural Networks▼1361.33
[PDF]Answer Candidates Reshape Language Model Decisions: Layer-wise Dynamics and Causal State Interventions▲6.1k2.00
[PDF]Localization Does Not Guarantee Control: Gate Failure and Partial Activation Steering in a Causal Reasoning Model▼1.2k1.67
[PDF]Training Selects Among Behaviorally Equivalent Computations in In-Context Dictionary Learning▲5.4k3.00
Withdrawn or desk rejected (152)
[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