© 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. 56568
    Prev
    Next
    INDEX
    Explanations

    defining main function or module

    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
    aisy
    -0.07
    afa
    -0.07
    ä¸ĬåĬł
    -0.07
     Ñģло
    -0.06
    entic
    -0.06
     betul
    -0.06
    Ö¼
    -0.06
    èľĤå·¢
    -0.06
    å©
    -0.06
    åIJİè¿Ľ
    -0.06
    POSITIVE LOGITS
    æĭ¯
    0.07
    dil
    0.07
    elow
    0.07
     Vald
    0.07
    emann
    0.07
    Ģ
    0.07
    åį«ä¸ľ
    0.06
    rp
    0.06
    å¸ĮæľĽä½łä»¬
    0.06
    ç»ıæµİæĬĢæľ¯
    0.06
    Activations Density 0.001%

    No Known Activations