© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 10442
    Prev
    Next
    INDEX
    Explanations

    electron transport chain

    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
    inars
    -0.07
    éĶĭ
    -0.07
    imat
    -0.07
     crash
    -0.06
    æĸ°çŁ¥è¯Ĩ
    -0.06
    ilat
    -0.06
    room
    -0.06
     sinc
    -0.06
     Jam
    -0.06
    ForObject
    -0.06
    POSITIVE LOGITS
    connector
    0.09
     asymmetric
    0.08
    incy
    0.07
     Courtesy
    0.07
    uttle
    0.07
    agai
    0.07
    Å¡tÄĽ
    0.07
    uvia
    0.07
    ä»ĭ
    0.07
    Spi
    0.07
    Activations Density 0.009%

    No Known Activations