Logit-Contribution Scoring Identifies Non-Literal Retrieval Heads Paper • 2607.01002 • Published 6 days ago • 17
Running on CPU Upgrade 1 Aletheia's Quest Leaderboard 🔎 1 View the deception‑detection competition leaderboard
google/diffusiongemma-26B-A4B-it Image-Text-to-Text • 26B • Updated about 11 hours ago • 1.7M • 1.11k
nvidia/NVIDIA-Nemotron-3-Ultra-550B-A55B-NVFP4 Text Generation • 335B • Updated 12 days ago • 476k • • 239
Qwen-Scope: Turning Sparse Features into Development Tools for Large Language Models Paper • 2605.11887 • Published May 12 • 18
🔍 Interpretability & Analysis of LMs Collection Outstanding research in LM interpretability and evaluation, summarized • 136 items • Updated May 26 • 119
Faithfulness Metrics Don't Measure Faithfulness: A Meta-Evaluation with Ground Truth Paper • 2605.25052 • Published May 24 • 14