The World Inside Neural Networks

{
  "url": "https://www.goodfire.ai/research/the-world-inside-neural-networks",
  "tags": [
    "mechanistic-interpretability",
    "neural-geometry",
    "representation-manifolds",
    "mountain-car",
    "SAE-critique",
    "goodfire"
  ],
  "year": 2026,
  "saved": "2026-05-14",
  "title": "The World Inside Neural Networks",
  "venue": "Goodfire research post (research article — may have arXiv companion)",
  "status": "summary-only",
  "authors": [
    "Atticus Geiger",
    "Ekdeep Singh Lubana",
    "Thomas Fel",
    "Jack Merullo",
    "Michael Jae Byun",
    "Owen Lewis",
    "Thomas McGrath"
  ],
  "published": "2026-05-07",
  "affiliation": "Goodfire (+ collaborators)"
}