{
  "id": 9463050,
  "title": "Hidden not Deleted: How Networks Suppress Entangled Features",
  "url": "https://urgent.news/2026/09/23/hidden-not-deleted-how-networks-suppress-entangled-features",
  "topic": "ai",
  "section": "AI",
  "published": "2026-09-23T09:10:12.000Z",
  "source": {
    "name": "arXiv cs.AI",
    "slug": "arxiv-cs-ai",
    "url": "https://arxiv.org/abs/2609.27593v1"
  },
  "original_language": "en",
  "account": null,
  "summary": "Concept erasure methods that operate via linear projection assume that features occupy separable subspaces. We show this assumption fails under dense superposition: when two features are forced into an antipodal pair sharing a single subspace, state-of-the-art linear erasure destroys both, not just the target. Networks trained with gradient descent instead solve this problem non-linearly, but not…",
  "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."
}