© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 29754
    Prev
    Next
    INDEX
    Explanations

    numbers followed by punctuation or units

    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
    hin
    -0.08
    trad
    -0.07
    angk
    -0.07
    ÑģÑĮ
    -0.07
    stag
    -0.07
    Trad
    -0.07
    Æ°Æ¡m
    -0.06
    ogh
    -0.06
    æĿĪ
    -0.06
    ocz
    -0.06
    POSITIVE LOGITS
    uffy
    0.08
    yiz
    0.07
    лик
    0.07
     Commission
    0.07
    ensed
    0.07
    ontos
    0.07
    ç¾İä¸Ń
    0.06
    ako
    0.06
    .bz
    0.06
    æµģåĬ¨çļĦ
    0.06
    Activations Density 0.015%

    No Known Activations