© 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. 13458
    Prev
    Next
    INDEX
    Explanations

    SP list, AV player, Path object

    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
    leston
    -0.07
    ä¸ŃåĽ½æ¢¦
    -0.07
    ommel
    -0.07
    riques
    -0.07
    é»į
    -0.07
    ı
    -0.07
     Forgotten
    -0.07
    edy
    -0.06
     ToString
    -0.06
    å¾Ĺ人
    -0.06
    POSITIVE LOGITS
    _DECLARE
    0.08
     âĤ¬*
    0.07
    .tem
    0.07
    :'+
    0.07
    ç±»åŀĭçļĦ
    0.07
    wali
    0.07
    дим
    0.07
    yped
    0.07
    kla
    0.06
    ARGE
    0.06
    Activations Density 0.099%

    No Known Activations