© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen2.5-7B-IT
    5. 20-MATRYOSHKA-65K
    7. 4120
    Prev
    Next
    INDEX
    Explanations

    news reports

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    chanind/qwen2.5-7B-it-layer-20-saes/pile/matryoshka/k-100
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    .optString
    -0.22
    _prefs
    -0.22
    廨
    -0.22
    toISOString
    -0.21
     RectTransform
    -0.21
    otionEvent
    -0.21
    **)&
    -0.20
    illac
    -0.20
     **)&
    -0.20
    ")));
    -0.20
    POSITIVE LOGITS
    å¼Ģå¥ĸç»ĵæŀľ
    0.28
    essim
    0.23
     newY
    0.22
     womens
    0.21
     "";č↵č↵
    0.20
     AFP
    0.20
    æľĭåıĭ们对
    0.20
     suche
    0.20
    æĴĻ
    0.19
     Bild
    0.19
    Activations Density 0.655%

    No Known Activations