© 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. 30596
    Prev
    Next
    INDEX
    Explanations

    due to

    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
    sev
    -0.09
    lah
    -0.09
    æĸ°åĬłåĿ¡
    -0.08
    ìļĶ
    -0.08
    ãģļãģ¤
    -0.08
    shire
    -0.08
    ric
    -0.07
    à¹ĥหà¸įà¹Ī
    -0.07
    chaft
    -0.07
    neur
    -0.07
    POSITIVE LOGITS
    ç§įç§įåİŁåĽł
    0.13
    åIJĦç§įåİŁåĽł
    0.11
     adanya
    0.09
    åħ¶åľ¨
    0.09
    йма
    0.08
    ä¸įå®Įåħ¨ç»Łè®¡
    0.08
    ages
    0.08
    ä¸ĢæŶçļĦ
    0.08
    uards
    0.07
    erschein
    0.07
    Activations Density 0.034%

    No Known Activations