© 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. 28290
    Prev
    Next
    INDEX
    Explanations

    categories and specific topics

    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
    egin
    -0.07
    ç«ĭçļĦ
    -0.07
    este
    -0.06
    åħ±æľī
    -0.06
    ä¸ĬåĴĮ
    -0.06
    ichter
    -0.06
    æĪIJç«ĭ以æĿ¥
    -0.06
    æħ·
    -0.06
    æŃ£æľ¬
    -0.06
    ym
    -0.06
    POSITIVE LOGITS
     ìĺ¨
    0.07
    cium
    0.07
    繫
    0.07
    _general
    0.07
    ×Ļר×Ķ
    0.06
    ç±»
    0.06
    .yahoo
    0.06
    èĭ¥æĹł
    0.06
    ä¸ĢèĪ¬
    0.06
    æĤ¨å½ĵåīįçļĦ
    0.06
    Activations Density 0.022%

    No Known Activations