© 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. 864
    Prev
    Next
    INDEX
    Explanations

    protein complex assembly and interaction

    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
    èĨĽ
    -0.07
     gân
    -0.07
     drain
    -0.06
     TestData
    -0.06
    éĩĩçĶ¨çļĦ
    -0.06
    æ¯ı天éĥ½æľī
    -0.06
    åŁ¹æ¤į
    -0.06
     dzi
    -0.06
    å½Ĵç»ĵ
    -0.06
    ½ij
    -0.06
    POSITIVE LOGITS
     proteins
    0.10
     assembled
    0.10
    亲åĴĮ
    0.09
     binding
    0.09
     mediator
    0.08
     assemble
    0.08
    åĬŁèĥ½éļľç¢į
    0.08
     assembling
    0.08
    亲åĴĮåĬĽ
    0.08
    è¿ŀæİ¥æľī
    0.08
    Activations Density 0.262%

    No Known Activations