© 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. 18701
    Prev
    Next
    INDEX
    Explanations

    code or technical writing

    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
    ibri
    -0.08
    该åIJį
    -0.08
    nacht
    -0.08
    vard
    -0.07
    个头
    -0.07
    ä¸įåIJĥ
    -0.07
    Got
    -0.07
    è¿Ļ个人
    -0.07
    lez
    -0.06
    åı¹äºĨåı£æ°Ķ
    -0.06
    POSITIVE LOGITS
    ä¸ĭéĿ¢å°±
    0.08
    æºĸåĤĻ
    0.07
    yiz
    0.07
    ä¸ĭéĿ¢æĪij们
    0.07
    ä»Ĺ
    0.07
    æľ¬æĸĩå°Ĩä»İ
    0.07
     Sections
    0.06
    UIS
    0.06
    çļĦ缮çļĦæĺ¯
    0.06
    engo
    0.06
    Activations Density 0.001%

    No Known Activations