© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 37617
    Prev
    Next
    INDEX
    Explanations

    immediately, promptly, readily

    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
    Negative Logits
    kst
    -0.08
    czo
    -0.08
    ä¾µçĬ¯æĤ¨çļĦ
    -0.08
    ä»»ä½ķæŶåĢĻ
    -0.08
    عÙĪÙĨ
    -0.07
    gab
    -0.07
    ìĸ¸
    -0.07
     Coelho
    -0.07
    cased
    -0.07
    åħ¨éĿ¢èIJ½å®ŀ
    -0.07
    POSITIVE LOGITS
    对åħ¶è¿Ľè¡Į
    0.11
    第ä¸ĢæŶéĹ´
    0.11
    ç«ĭåĪ»
    0.11
     immediately
    0.11
     immediate
    0.10
    éļıä¹ĭ
    0.10
    ç«ĭåį³
    0.10
    éļıåį³
    0.10
     promptly
    0.09
    èĥ½åıĬæŶ
    0.09
    Activations Density 0.361%

    No Known Activations