© 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. 7698
    Prev
    Next
    INDEX
    Explanations

    analytic cookies

    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
    udou
    -0.09
    ä¹ĭé¤ĺ
    -0.08
    度ãĤĤ
    -0.08
    覧
    -0.08
    ارÙĩ
    -0.08
    ulet
    -0.08
    .pe
    -0.07
    ç½ijé¦ĸ页
    -0.07
     omas
    -0.07
    éģ
    -0.07
    POSITIVE LOGITS
    åŀĭåĴĮ
    0.13
    åŀĭ
    0.13
    åŀĭçļĦ
    0.11
    -based
    0.11
    å¼ı
    0.10
    -type
    0.10
    å¼ı设计
    0.09
    å¼ıåĴĮ
    0.09
     type
    0.09
    -Based
    0.09
    Activations Density 0.350%

    No Known Activations