© 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. 16667
    Prev
    Next
    INDEX
    Explanations

    illustrates, depicts, shows, describes

    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
    æĬ¥è®¯
    -0.08
    æĭīéĩĮ
    -0.08
    ç§ī
    -0.07
    ully
    -0.07
    æĸ°ä¹¦
    -0.06
    åIJįåī¯
    -0.06
    /DTD
    -0.06
    à¸ģลà¸ĩ
    -0.06
    oulder
    -0.06
     yourselves
    -0.06
    POSITIVE LOGITS
    åĴĮ第
    0.08
    <|box_end|>
    0.07
    ustos
    0.07
    ä¼ĹæīĢåij¨çŁ¥
    0.07
    tig
    0.07
    asher
    0.07
    ä¸ºåŁºç¡Ģ
    0.06
    дав
    0.06
    ten
    0.06
    TERS
    0.06
    Activations Density 0.223%

    No Known Activations