© 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. 18370
    Prev
    Next
    INDEX
    Explanations

    before I

    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
    eding
    -0.07
     ÑĥÑĤÑĢо
    -0.07
    /ms
    -0.07
    urit
    -0.07
    å¼Ģå§ĭåIJİ
    -0.07
    第ä¸Ģéĥ¨
    -0.06
    天河
    -0.06
    idd
    -0.06
    æĺ¥æĿ¥
    -0.06
    æĪIJ为ä¸ŃåĽ½
    -0.06
    POSITIVE LOGITS
     **¡
    0.07
     **—
    0.07
     nhắc
    0.07
    ç¡®
    0.07
     gian
    0.07
     **¿
    0.07
    ytt
    0.07
     кое
    0.07
    vetica
    0.07
    为äºĨæĽ´å¥½åľ°
    0.07
    Activations Density 0.010%

    No Known Activations