© 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. 18348
    Prev
    Next
    INDEX
    Explanations

    programming languages and code

    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
    è¿İéĿ¢
    -0.07
    ä¸ĢéĹª
    -0.06
     Matr
    -0.06
    å¤ĸåŀĭ
    -0.06
    hr
    -0.06
    èĽĨ
    -0.06
    å¿Ĺ强
    -0.06
    æ´
    -0.06
    æ°Ľ
    -0.06
    åIJĦèĩªçļĦ
    -0.06
    POSITIVE LOGITS
     code
    0.08
    趣
    0.07
    lite
    0.07
    åĮĸåIJį
    0.07
    è¯Ńåı¥
    0.07
     abstract
    0.07
     version
    0.07
    makta
    0.07
    à°µà±ģ
    0.07
     import
    0.07
    Activations Density 0.011%

    No Known Activations