© 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. 64436
    Prev
    Next
    INDEX
    Explanations

    translation metadata

    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»įåŃĺåľ¨
    -0.08
    ÑĢик
    -0.07
    缤
    -0.07
    eret
    -0.07
    ensus
    -0.07
    ä¼¼æĺ¯
    -0.07
    à¤Łà¤ķ
    -0.07
    åķĨåĬ¡æľįåĬ¡
    -0.07
    ´Ģ
    -0.07
    åı¯è°ĵæĺ¯
    -0.07
    POSITIVE LOGITS
    大æĦı
    0.08
    à¸ķุ
    0.07
    è¯ĿæĿ¥
    0.07
    éĩĮåİ»
    0.06
    aign
    0.06
     Bulls
    0.06
    大å¥ĸ
    0.06
    æĸ°åıijå±ķ
    0.06
    दि
    0.06
    信義
    0.06
    Activations Density 0.034%

    No Known Activations