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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 23886
    Prev
    Next
    INDEX
    Explanations

    ARG followed by number

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    æ´ģ
    -0.06
    壤
    -0.06
    erre
    -0.06
    aset
    -0.06
    emia
    -0.06
    ª½
    -0.06
     ?,
    -0.06
    reta
    -0.06
    /*.
    -0.06
     natura
    -0.06
    POSITIVE LOGITS
    ottom
    0.08
    ugs
    0.08
    请åijĬçŁ¥
    0.07
    åºĨç¥Ŀä¸ŃåĽ½åħ±äº§åħļæĪIJç«ĭ
    0.07
    _verbose
    0.07
    ensi
    0.07
    `;
    0.07
    ktes
    0.07
    udi
    0.07
    -done
    0.07
    Activations Density 0.125%

    No Known Activations