© 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. 31129
    Prev
    Next
    INDEX
    Explanations

    pagecontrol, random, Handbook

    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
    æ¡ĤåĽŃ
    -0.08
    åľ¨èIJ¥
    -0.07
    ÑĮÑĤе
    -0.06
    :not
    -0.06
    个ä¸įåģľ
    -0.06
    owani
    -0.06
    èIJ½çļĦ
    -0.06
    vlak
    -0.06
    Ùħز
    -0.06
    agne
    -0.06
    POSITIVE LOGITS
    gau
    0.08
    ähn
    0.08
    -like
    0.07
    ischer
    0.07
    ä¸īè¦ģ
    0.07
    uks
    0.07
    -toggler
    0.07
    -ish
    0.07
    anter
    0.07
    çļĭ
    0.07
    Activations Density 0.017%

    No Known Activations