{
    "@id": "https://newmindmuseum.com/topics/mechanistic-interpretability/#entity",
    "id": "tema/mechanistic-interpretability",
    "type": "DefinedTerm",
    "name": "Mechanistic interpretability",
    "description": "reverse-engineering neural networks",
    "url": "https://newmindmuseum.com/topics/mechanistic-interpretability/",
    "sameAs": [
        "https://www.wikidata.org/wiki/Q134503305",
        "https://en.wikipedia.org/wiki/Mechanistic_interpretability"
    ],
    "wikidata": "Q134503305",
    "stories": [
        {
            "title": "What happens inside an AI when it answers you?",
            "url": "https://newmindmuseum.com/interpretability/2026/11/what-happens-inside-ai-when-it-answers-you/",
            "date": "2026-11-14",
            "data": "https://newmindmuseum.com/interpretability/2026/11/what-happens-inside-ai-when-it-answers-you/data.json"
        },
        {
            "title": "Tracing the thoughts of a language model, explained",
            "url": "https://newmindmuseum.com/interpretability/2026/11/tracing-thoughts-language-model-anthropic-explained/",
            "date": "2026-11-06",
            "data": "https://newmindmuseum.com/interpretability/2026/11/tracing-thoughts-language-model-anthropic-explained/data.json"
        },
        {
            "title": "Golden Gate Claude: the day an AI model became obsessed with a bridge",
            "url": "https://newmindmuseum.com/interpretability/2026/11/golden-gate-claude-interpretability-demo/",
            "date": "2026-11-06",
            "data": "https://newmindmuseum.com/interpretability/2026/11/golden-gate-claude-interpretability-demo/data.json"
        }
    ],
    "license": "https://creativecommons.org/licenses/by/4.0/"
}