© 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. 60420
    Prev
    Next
    INDEX
    Explanations

    unsafe code constructs

    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
    coli
    -0.07
    ewe
    -0.06
    اث
    -0.06
    ünd
    -0.06
    oured
    -0.06
    人æĿ¥
    -0.06
    为æİ¨è¿Ľ
    -0.06
    ç»ıéªĮ
    -0.06
    ¦
    -0.06
    _ROWS
    -0.06
    POSITIVE LOGITS
    новÑĮ
    0.08
    extras
    0.08
    isplay
    0.08
    utate
    0.08
    ecu
    0.07
     cÆ°á»Ŀng
    0.07
    è¼Ķ
    0.07
    nesday
    0.07
    woord
    0.07
    ;display
    0.07
    Activations Density 0.552%

    No Known Activations