© 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. 20208
    Prev
    Next
    INDEX
    Explanations

    code blocks

    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
    epend
    -0.08
     PageSize
    -0.07
    åĬªåĬĽå®ŀçİ°
    -0.07
    ä¸įåĩº
    -0.07
    ë°Ķë¡ľ
    -0.07
    omÄĽ
    -0.07
    尼奥
    -0.07
    paren
    -0.07
    ÙĦع
    -0.07
    综
    -0.07
    POSITIVE LOGITS
    ahas
    0.09
     اÙĨÙĪاع
    0.07
    æıIJä¾ĽåIJĦç§į
    0.06
     znac
    0.06
     gran
    0.06
    hee
    0.06
     nuances
    0.06
     several
    0.06
    ä¸įåIJĮç±»åŀĭ
    0.06
     exceptions
    0.06
    Activations Density 0.016%

    No Known Activations