© 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. 61096
    Prev
    Next
    INDEX
    Explanations

    other or else

    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
    åIJİèĢħ
    -0.08
    è¡·
    -0.07
    æľĢåıĹ欢è¿İ
    -0.07
    çļĦåħ¨è¿ĩç¨ĭ
    -0.07
    æĸ¹å¼ıæĿ¥
    -0.07
    ä½Ĩåħ¶
    -0.07
    ä¸įåIJĮçļĦ人
    -0.07
    ame
    -0.07
     underlying
    -0.06
    è¿Ļæł·ä¸Ģ个
    -0.06
    POSITIVE LOGITS
     ones
    0.10
    otros
    0.08
     demás
    0.08
    åħ¶ä½Ļ
    0.08
    others
    0.08
     others
    0.08
    è¦ģä¹Ī
    0.08
    è¦ģä¹Īæĺ¯
    0.07
    stående
    0.07
    éĥ½æĺ¯ä¸ĢäºĽ
    0.07
    Activations Density 0.011%

    No Known Activations