© 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. 18822
    Prev
    Next
    INDEX
    Explanations

    circular race track of radius

    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
    æĹ¥æĿ¥
    -0.07
    obot
    -0.07
    anea
    -0.07
     infatti
    -0.06
    åľ¨ä¸Ĭ
    -0.06
     ÑĢазве
    -0.06
    uky
    -0.06
    åģļçļĦæĺ¯
    -0.06
    niÄĻ
    -0.06
    å¼Ģå±ķ好
    -0.06
    POSITIVE LOGITS
    anty
    0.08
    asar
    0.08
    estig
    0.07
    казÑĭваеÑĤÑģÑı
    0.07
    ugna
    0.07
    onder
    0.07
    asaran
    0.07
    ستÙĩا
    0.07
    丽èIJį
    0.07
    _SUS
    0.06
    Activations Density 0.526%

    No Known Activations