© 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. 46066
    Prev
    Next
    INDEX
    Explanations

    numbers following punctuation

    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
    寮
    -0.08
    ondi
    -0.08
    aseline
    -0.07
    ebo
    -0.07
    entiel
    -0.07
    ijke
    -0.07
    ỾI
    -0.07
    arau
    -0.07
    _finder
    -0.07
    ereal
    -0.07
    POSITIVE LOGITS
    zung
    0.07
    TO
    0.06
    ä¸Ĭ大åѦ
    0.06
    _",
    0.06
    æĮ
    0.06
    Feat
    0.06
    riv
    0.06
    lici
    0.06
    íķĺìĭľ
    0.06
    สัà¸Ļ
    0.06
    Activations Density 0.018%

    No Known Activations