© 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. 47000
    Prev
    Next
    INDEX
    Explanations

    Dirk

    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
    êµīìŀ¥
    -0.08
    꽤
    -0.07
    主ä¹ī
    -0.07
    ç»Ļ人
    -0.07
    otope
    -0.07
    说ä¸įåĩºçļĦ
    -0.07
    ÄĥtÄĥ
    -0.07
    zyme
    -0.07
    ìĮ¤
    -0.07
    èĥľ
    -0.07
    POSITIVE LOGITS
    kens
    0.07
    enstein
    0.06
    anis
    0.06
    гое
    0.06
    ı
    0.06
     Ern
    0.06
    íĥľ
    0.06
    xies
    0.06
    åIJįæĢĿ
    0.06
    dpi
    0.06
    Activations Density 0.025%

    No Known Activations