© 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. 1412
    Prev
    Next
    INDEX
    Explanations

    code structures and programming languages

    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
    åĸľæĢĴåĵĢ
    -0.08
    anat
    -0.08
    pis
    -0.07
    OTS
    -0.07
     BITS
    -0.07
    alytics
    -0.07
    menes
    -0.07
    èĮ¨
    -0.07
    Ùĭ
    -0.07
    äck
    -0.06
    POSITIVE LOGITS
    sel
    0.07
    unnel
    0.07
    ¹
    0.07
     fr
    0.06
    人æĿ¥è¯´
    0.06
    agh
    0.06
    çļĦ人æĿ¥è¯´
    0.06
    åį³åľ¨
    0.06
    æł¼æĸ¯
    0.06
    unn
    0.06
    Activations Density 0.093%

    No Known Activations