© 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. 57468
    Prev
    Next
    INDEX
    Explanations

    major league baseball

    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
    缸åħ³äº§åĵģ
    -0.08
     Sidd
    -0.07
    /cmd
    -0.07
    å¤Ł
    -0.06
    stored
    -0.06
    ä¸įæ²»
    -0.06
    å¤ļ家
    -0.06
    æĹłèĻij
    -0.06
     related
    -0.06
    loo
    -0.06
    POSITIVE LOGITS
    çļĦåIJĦ个
    0.08
    åIJĦ个
    0.08
    oplan
    0.08
    ìłĪìĿĦ
    0.08
    çļĦæīĢæľī
    0.08
    çļĦä¸įåIJĮ
    0.08
    -main
    0.07
    zil
    0.07
    çķĻè¨ĢæĿ¿
    0.07
    å¡ŀ
    0.07
    Activations Density 0.432%

    No Known Activations