© 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. 24593
    Prev
    Next
    INDEX
    Explanations

    import paths

    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
    ód
    -0.07
    ines
    -0.06
    ysi
    -0.06
    æĢ»æ¯Ķ
    -0.06
    uros
    -0.06
    _tbl
    -0.06
    é©®
    -0.06
     snap
    -0.06
    ÑĢазÑĥ
    -0.06
    keer
    -0.06
    POSITIVE LOGITS
    è¦ģæĪij
    0.08
    igate
    0.08
    .Lib
    0.07
    汽车éĶĢåĶ®æľįåĬ¡æľīéĻIJåħ¬åı¸
    0.07
    -Token
    0.07
    acre
    0.07
    ãģ¹
    0.06
    ,state
    0.06
     Haber
    0.06
    rick
    0.06
    Activations Density 0.179%

    No Known Activations