© 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. 44946
    Prev
    Next
    INDEX
    Explanations

    higher effect, coherent patterns, profound effect

    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
    丽人
    -0.07
    çĪ±æĪij
    -0.07
    EGI
    -0.07
    è°ĭåıijå±ķ
    -0.07
    è¿Ļåı«
    -0.06
    ä¹Łæĺ¯æľĢ
    -0.06
    øm
    -0.06
    èİĨ
    -0.06
    ç¨İåĬ¡å±Ģ
    -0.06
    ä½łæ°¸è¿ľ
    -0.06
    POSITIVE LOGITS
    åı¯èĥ½æĺ¯
    0.08
    åľ¨ä»ĬåIJİ
    0.07
    probably
    0.07
    astia
    0.07
    ardin
    0.07
     probably
    0.07
     apparently
    0.07
    ä»ĬåIJİ
    0.07
    çŁŃæŶéĹ´
    0.07
    è¿Ļåı¯èĥ½æĺ¯
    0.07
    Activations Density 0.648%

    No Known Activations