© 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. 7355
    Prev
    Next
    INDEX
    Explanations

    chapters

    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
    两ç§įæĸ¹å¼ı
    -0.06
    ä¸īèĢħ
    -0.06
    ä½Ļ
    -0.06
    éĢı
    -0.06
    第äºĶå±Ĭ
    -0.06
    oir
    -0.06
    åħ³äºİæĪij们
    -0.06
    èĩ´
    -0.06
    readcrumb
    -0.06
    饱
    -0.06
    POSITIVE LOGITS
    éĢIJ个
    0.19
    æ¯ı个
    0.18
    ä¸Ģ个个
    0.18
     each
    0.17
    (each
    0.17
    éĢIJä¸Ģ
    0.17
     Each
    0.17
    æ¯ıä¸Ģ个
    0.17
    æ¯ıåĢĭ
    0.17
    æ¯ıæĿ¡
    0.16
    Activations Density 0.504%

    No Known Activations