© 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. 61419
    Prev
    Next
    INDEX
    Explanations

    questions about examples or specific items

    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
     Actualités
    -0.07
    éŁŃ
    -0.07
    ronym
    -0.07
    abort
    -0.07
    -minus
    -0.07
    ä¸ĩåĽ½
    -0.07
    rade
    -0.07
     theoretically
    -0.07
    ÑĦоÑĢми
    -0.07
    æĺ¯ä»Ģä¹Īåij¢
    -0.06
    POSITIVE LOGITS
    æѤ类
    0.09
     suelen
    0.09
    å¾Ģå¾Ģ
    0.08
    éĢļ常æĺ¯
    0.08
    è¿Ļç±»
    0.08
    å¾Ģå¾Ģæĺ¯
    0.08
     often
    0.08
     подобного
    0.08
    éĢļ常
    0.08
    éĢļå¸¸åľ¨
    0.08
    Activations Density 0.019%

    No Known Activations