© 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. 64658
    Prev
    Next
    INDEX
    Explanations

    not concerned with

    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
    ä¸į离
    -0.07
    enes
    -0.07
    åĽłä¸ºä½ł
    -0.07
    :title
    -0.07
    _SUP
    -0.07
     Publié
    -0.07
    ضÙĬØ©
    -0.07
     genoeg
    -0.07
    ëªħìĨĮ
    -0.07
    .Callback
    -0.07
    POSITIVE LOGITS
     worrying
    0.08
    ak
    0.07
    æĭħå¿ĥ
    0.07
    ä¸įå¤ļ说
    0.07
    ow
    0.07
    è¿Ļæĸ¹éĿ¢çļĦ
    0.07
    ä¸įçĶ¨æĭħå¿ĥ
    0.07
     moot
    0.06
    åIJ«
    0.06
     worry
    0.06
    Activations Density 0.037%

    No Known Activations