© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 16344
    Prev
    Next
    INDEX
    Explanations

    UNITED STATES of America

    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
    /ajax
    -0.07
    ç»ı
    -0.07
    /
    -0.07
    æĢĿè·¯åĴĮ
    -0.07
    à¥įह
    -0.06
    çŁŃæľŁçļĦ
    -0.06
    éĢļçĶ¨çļĦ
    -0.06
    ulas
    -0.06
    åĮ»åѦè§Ĥå¯Ł
    -0.06
    \\\\
    -0.06
    POSITIVE LOGITS
    oksi
    0.09
    osten
    0.08
     ÑĥÑģловий
    0.07
    kurat
    0.07
     knull
    0.07
    Ùijا
    0.07
    dden
    0.07
    BOT
    0.07
     ÐļÑĢаÑģи
    0.07
    ι
    0.07
    Activations Density 0.001%

    No Known Activations