© 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. 52156
    Prev
    Next
    INDEX
    Explanations

    equilibrium binding

    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
    åĦ¿çļĦ
    -0.09
    orna
    -0.08
    itive
    -0.08
    новÑĮ
    -0.08
    ionate
    -0.08
    ivate
    -0.08
    ÏĦεÏģ
    -0.08
    /email
    -0.08
    mith
    -0.08
    æļĤè¡Įè§Ħå®ļ
    -0.08
    POSITIVE LOGITS
    ยà¹Į
    0.10
    anche
    0.09
    çĬ¶æĢģ
    0.08
    phas
    0.08
    çĬ¶æĢģä¸ĭ
    0.08
    çļĦãģª
    0.07
    asking
    0.07
    ilibrium
    0.07
    è¿Ļæł·æĤ¨å°±åı¯ä»¥
    0.07
    ijIJ
    0.07
    Activations Density 0.005%

    No Known Activations