{"total":8,"rows":[{"id":"2511.08579","title":"Training Language Models to Explain Their Own Computations","created":"2025-11-11","cited_by_count":30,"area":null},{"id":"2505.17495","title":"ProxySPEX: Inference-Efficient Interpretability via Sparse Feature Interactions in LLMs","created":"2025-05-23","cited_by_count":16,"area":null},{"id":"2502.13870","title":"SPEX: Scaling Feature Interaction Explanations for LLMs","created":"2025-02-19","cited_by_count":12,"area":null},{"id":"2505.15807","title":"The Atlas of In-Context Learning: How Attention Heads Shape In-Context Retrieval Augmentation","created":"2025-05-21","cited_by_count":11,"area":null},{"id":"2502.15801","title":"An explainable transformer circuit for compositional generalization","created":"2025-02-19","cited_by_count":8,"area":null},{"id":"2605.30233","title":"Do Language Models Track Entities Across State Changes?","created":"2026-05-28","cited_by_count":6,"area":null},{"id":"2601.10266","title":"Measuring Affinity between Attention-Head Weight Subspaces via the Projection Kernel","created":"2026-01-15","cited_by_count":5,"area":null},{"id":"2609.07183","title":"CircuitLens: Reasoning Circuits as Data Selection Signals for Reinforcement Learning with Verifiable Rewards","created":"2026-09-07","cited_by_count":1,"area":null}],"next_cursor":null}