© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen2.5-7B-IT
    5. 20-MATRYOSHKA-65K
    7. 711
    Prev
    Next
    INDEX
    Explanations

    Listing information

    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
    Not in Any Lists

    No Comments

    Negative Logits
    çĽijåIJ¬é¡µéĿ¢
    -0.29
    .Disclaimer
    -0.29
    _REFERER
    -0.28
    åľ¨çݩ家
    -0.24
    âĨĻ
    -0.24
    ċ
    -0.23
    çļĦ带é¢Ĩ
    -0.23
    罡
    -0.23
    quiries
    -0.23
    æĹ¶ä»£ä¸ŃåĽ½
    -0.23
    POSITIVE LOGITS
    ç¥Ľæĸij
    0.29
    paralleled
    0.27
    ä¸ī大éĺ¶æ®µ
    0.22
     Nearby
    0.21
     PointF
    0.21
    ãĤĴè¦ĭãĤĭ
    0.21
     libertin
    0.20
    mouseup
    0.20
    -deals
    0.20
     ResourceBundle
    0.20
    Activations Density 3.859%

    No Known Activations