© 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. 1710
    Prev
    Next
    INDEX
    Explanations

    prefix followed by suffix

    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
    人äºĨ
    -0.08
    è¿ĶåĽŀ顶éĥ¨
    -0.08
    çļĦ人æĿ¥è¯´
    -0.08
    дела
    -0.08
    plevel
    -0.08
    avior
    -0.07
    Ú¯ÛĮ
    -0.07
    ÑĦÑĤе
    -0.07
    ugged
    -0.07
    æĸĩç«łäºĨ
    -0.07
    POSITIVE LOGITS
    orem
    0.09
     infatti
    0.08
    æ³ķæĺ¯
    0.08
    ä¹ĭæīĢ以
    0.08
    ä¸Ģè¯į
    0.08
    æĢ§æĺ¯
    0.07
    æĭħè´Ł
    0.07
    rc
    0.07
    æĺ¯ä¸Ģ个å¾Ī
    0.07
    ola
    0.07
    Activations Density 0.211%

    No Known Activations