© 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. 10422
    Prev
    Next
    INDEX
    Explanations

    mixed language characters

    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
    è·¯ä¸İ
    -0.08
    ahir
    -0.08
    ï¼Ŀï¼Ŀï¼Ŀï¼Ŀ
    -0.08
    ãĢįãĢģãĢĮ
    -0.07
    ãģ¨ãģĦãģĨãģĭ
    -0.07
    ?”,
    -0.07
    !».
    -0.07
     certes
    -0.07
    ä¸įä½Ĩ
    -0.07
    ä¿¡æģ¯ä¸İ
    -0.07
    POSITIVE LOGITS
     lainnya
    0.07
    åĻ¨çŃī
    0.07
    以æѤ
    0.07
    âĢİ
    0.06
    管çIJĨçŃī
    0.06
     noqa
    0.06
     alike
    0.06
    å°±åľ¨è¿ĻéĩĮ
    0.06
    ä¸ĭåIJĮ
    0.06
    æľįåĬ¡çŃī
    0.06
    Activations Density 0.803%

    No Known Activations