© 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. 31328
    Prev
    Next
    INDEX
    Explanations

    experience hunter

    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
    osso
    -0.06
    ìŀ¡
    -0.06
    eret
    -0.06
    _invoke
    -0.06
    .Must
    -0.06
    isky
    -0.06
    utils
    -0.06
    stra
    -0.06
    µ
    -0.06
    voi
    -0.06
    POSITIVE LOGITS
    uchia
    0.08
    顾åIJįæĢĿä¹ī
    0.08
    ä½Ĩä¸įéĻIJäºİ
    0.08
     berp
    0.07
    æĺ¯æĮĩåľ¨
    0.07
    鸳
    0.07
    æľ¬æ³ķ
    0.07
    个人æĪĸ
    0.07
    ahrenheit
    0.07
    _INCLUDED
    0.07
    Activations Density 0.009%

    No Known Activations