© 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. 39453
    Prev
    Next
    INDEX
    Explanations

    calculation/aggregation/summation

    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¿Ļç§įä¸ľè¥¿
    -0.07
    çij
    -0.07
    è¿Ļä¸ªä¸ľè¥¿
    -0.07
    opportun
    -0.07
    è¿Ļç§įæĥħåĨµ
    -0.07
    _DRAW
    -0.07
     deal
    -0.07
    isert
    -0.06
    è¿Ļ个éģĵçIJĨ
    -0.06
    使çĶ¨çļĦæĺ¯
    -0.06
    POSITIVE LOGITS
    计ç®Ĺåĩº
    0.10
    ucin
    0.08
    oreach
    0.08
    æ²¹çĽIJ
    0.08
    åĮħæĭ¬ä½Ĩä¸įéĻIJäºİ
    0.08
    åľ¨æ¯ı个
    0.07
    KNOWN
    0.07
    å¦ĤæѤä¸ĢæĿ¥
    0.07
    个æĪĸå¤ļ个
    0.07
    åĪĻ该
    0.07
    Activations Density 0.003%

    No Known Activations