© 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. 38235
    Prev
    Next
    INDEX
    Explanations

    population of groups

    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
    åĪĻå°Ĩ
    -0.08
     souvent
    -0.08
     often
    -0.07
    åĪĻåı¯
    -0.07
    æĸ¹éĿ¢ä¹Ł
    -0.07
     oft
    -0.07
    主è¦ģæĺ¯éĢļè¿ĩ
    -0.07
     spesso
    -0.07
    ://{
    -0.07
    èĢĮåĩº
    -0.07
    POSITIVE LOGITS
    åĨį说äºĨ
    0.08
    äºīå½ĵ
    0.08
    ä¸įåIJĮç¨ĭ度
    0.08
    æĪĸ以ä¸Ĭ
    0.07
    Decorator
    0.07
    ç¦ģä¸įä½ı
    0.07
    ystems
    0.07
    ä¸ļåĬ¡æ°´å¹³
    0.07
    ä¸įåIJĮç¨ĭ度çļĦ
    0.07
    /books
    0.07
    Activations Density 0.059%

    No Known Activations