© 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. 8373
    Prev
    Next
    INDEX
    Explanations

    latex math formatting

    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
    IPPING
    -0.07
    æľ¬ç«ł
    -0.07
    çļĩåŃIJ
    -0.07
    มั
    -0.07
    åĪĨæł¡
    -0.07
    åĵģè´¨åĴĮ
    -0.06
     dég
    -0.06
    åĴĮåIJĦç§į
    -0.06
    éĥ¨ç½²
    -0.06
    èĮī
    -0.06
    POSITIVE LOGITS
    æĢª
    0.07
    ossal
    0.07
    -spe
    0.07
    ÏĮÏĦε
    0.07
    logg
    0.07
    veu
    0.07
    ç´¯
    0.07
     Cra
    0.06
    abis
    0.06
    åIJ¸
    0.06
    Activations Density 0.012%

    No Known Activations