© 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. 4738
    Prev
    Next
    INDEX
    Explanations

    kinetics and reactions

    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
    ç§ĭæľĪ
    -0.09
    åľ¨èIJ¥
    -0.08
    é«Ķéĩį
    -0.08
    æĺ¯éĽĨ
    -0.08
    _pel
    -0.08
    Locator
    -0.07
    åįİéĺ³
    -0.07
    flate
    -0.07
    æ²īéĩį
    -0.07
    ä¸īåı·
    -0.07
    POSITIVE LOGITS
    åĮĸåѦåıįåºĶ
    0.09
     kinetics
    0.08
     molec
    0.08
     Reaction
    0.08
     reaction
    0.08
     enzyme
    0.08
     catalyst
    0.08
    åĤ¬åĮĸåīĤ
    0.08
    åıįåºĶ
    0.07
    éĢŁçİĩ
    0.07
    Activations Density 0.003%

    No Known Activations