© 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. 52198
    Prev
    Next
    INDEX
    Explanations

    sixty carbon atoms, hexagonal, polygon

    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
    äººæľº
    -0.08
    åıªè¦ģåľ¨
    -0.08
    æĺ¯ä¸Ģ个人
    -0.08
    éĩıåĬĽ
    -0.08
    yster
    -0.07
    å¾®éĩı
    -0.07
    zinho
    -0.07
     Tune
    -0.07
    acas
    -0.07
    é¢Ĩå·¾
    -0.07
    POSITIVE LOGITS
    emen
    0.08
    pagesize
    0.08
     polygon
    0.07
    evas
    0.07
     convex
    0.07
     "\",
    0.07
    aille
    0.07
    åĽ¾æ¡Ī
    0.07
     polygons
    0.07
    groupBy
    0.07
    Activations Density 0.003%

    No Known Activations