© 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. 44523
    Prev
    Next
    INDEX
    Explanations

    name followed by colon

    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
    ä¸īæĪIJ
    -0.07
    ovina
    -0.07
    udos
    -0.07
    [/
    -0.07
    åħŃæĪIJ
    -0.07
    avig
    -0.06
     Weinstein
    -0.06
    adini
    -0.06
    bach
    -0.06
     [/
    -0.06
    POSITIVE LOGITS
    коÑĤ
    0.08
    ê´´
    0.07
     Constructor
    0.07
     sklad
    0.07
    ãĥ¨
    0.07
    åıį対
    0.07
    oooooooo
    0.06
    å·¢
    0.06
    æ½ĩ
    0.06
    大åĬĽå®ŀæĸ½
    0.06
    Activations Density 0.281%

    No Known Activations