© 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. 58793
    Prev
    Next
    INDEX
    Explanations

    Subway cereal Lay PostgreSQL

    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
    éļıç¼ĺ
    -0.07
     presently
    -0.06
     Pase
    -0.06
     Shemale
    -0.06
    çĤ¹èĩ³
    -0.06
    ä½ĨæĦ¿
    -0.06
    usah
    -0.06
    çĮ¬
    -0.06
    arbe
    -0.06
    ellig
    -0.06
    POSITIVE LOGITS
    å°±æĺ¯åĽłä¸º
    0.08
    éĤ£æŶçļĦ
    0.08
    éĥ½æĺ¯éĢļè¿ĩ
    0.08
     damal
    0.08
    å½¢åĬ¿
    0.08
     damals
    0.08
    éĤ£æł·çļĦ
    0.07
    æĸĩæĺİåįķä½į
    0.07
    æĺİæĺİæĺ¯
    0.07
    éĤ£æŶ
    0.07
    Activations Density 0.025%

    No Known Activations