© 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. 42614
    Prev
    Next
    INDEX
    Explanations

    be 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
    ä¸įåIJĮç¨ĭ度
    -0.09
    æľĢåĢ¼å¾Ĺ
    -0.09
    æľ¬æĸĩéĵ¾æİ¥
    -0.08
     Sih
    -0.08
    æŀģ好
    -0.08
    çļĦèī¯å¥½
    -0.08
    ä¸įæĸŃæĽ´æĸ°
    -0.08
    åIJĦç§įä¸įåIJĮçļĦ
    -0.08
    emani
    -0.08
    orgeous
    -0.08
    POSITIVE LOGITS
    æĺİäºĨ
    0.08
    ç®Ģ
    0.08
     concise
    0.07
     bref
    0.06
    nov
    0.06
    æľį
    0.06
    æĿ¡çIJĨ
    0.06
    å®Ī
    0.06
    ÑģÑĭпа
    0.06
    ç®Ģæ´ģ
    0.06
    Activations Density 0.008%

    No Known Activations