© 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. 732
    Prev
    Next
    INDEX
    Explanations

    kinase and phosphorylation

    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
    sted
    -0.08
     voc
    -0.08
     Maire
    -0.07
    Ð¥Ðŀ
    -0.07
    æĤłæī¬
    -0.07
    åľ¨å¿ħ
    -0.07
    è´ªåĽ¾
    -0.07
    æ®ĭ缺
    -0.07
     geo
    -0.07
     ëĤ
    -0.07
    POSITIVE LOGITS
     phosphory
    0.09
     kinase
    0.07
     casc
    0.07
    imbus
    0.07
     cascade
    0.07
    ench
    0.07
    ellular
    0.07
    èĬĤåīį
    0.07
    Domains
    0.06
    asp
    0.06
    Activations Density 0.079%

    No Known Activations