{
  "id": 8161611,
  "title": "Deep Noir: Autonomous Steering Discovery via Architectural Chronometry in Transformer Models",
  "url": "https://urgent.news/2026/09/17/deep-noir-autonomous-steering-discovery-via-architectural-chronometry",
  "topic": "ai",
  "section": "AI",
  "published": "2026-09-17T17:16:31.000Z",
  "source": {
    "name": "arXiv cs.AI",
    "slug": "arxiv-cs-ai",
    "url": "https://arxiv.org/abs/2609.20722v1"
  },
  "original_language": "en",
  "account": null,
  "summary": "Activation steering modifies LLM behavior at inference time, but identifying where and how strongly to steer remains manual. We introduce Deep Noir, a framework that uses Logit Lens convergence and causal head-level attribution to autonomously discover optimal steering parameters. Across three scales (1B x 3, 2-3B x 2, and 7-9B x 4), our engine achieves 16.7 percentage-point improvement on spam…",
  "key_points": [],
  "editors_take": null,
  "illustration": null,
  "coverage": {
    "outlets": 1,
    "also_reported_by": []
  },
  "ai_generated": true,
  "disclaimer": "Summaries, key points and the editor’s take are written by software from other outlets’ reporting and may contain errors — always check the linked original."
}