© 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. 14053
    Prev
    Next
    INDEX
    Explanations

    ways to do something

    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
    æĺ¯ä¸įåı¯
    -0.08
    ä»ģåĴĮ
    -0.08
    ä¸įåı¯æĽ¿ä»£
    -0.08
    idor
    -0.08
    å¿ħä¸įåı¯
    -0.08
    зло
    -0.08
    пÑĤо
    -0.07
    assar
    -0.07
    ä¹Łä¸įåı¯
    -0.07
    çļĦåIJĦ项
    -0.07
    POSITIVE LOGITS
    ä¸Ģç§įæĺ¯
    0.10
     depending
    0.08
     ways
    0.07
    depending
    0.06
    in
    0.06
    åĩłç§į
    0.06
    otch
    0.06
     podej
    0.06
    åīį端
    0.06
    两ç§įæĸ¹å¼ı
    0.06
    Activations Density 0.048%

    No Known Activations