© 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. 34934
    Prev
    Next
    INDEX
    Explanations

    .org web services

    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
    utica
    -0.08
    yms
    -0.08
    á»iji
    -0.07
    åħ¼æĢ»ç»ıçIJĨ
    -0.07
    alem
    -0.07
    解æ¯Ĵ
    -0.07
    é¥®é£Łä¸Ĭ
    -0.07
    æĢ»æ¯Ķ
    -0.07
    并讲è¯Ŀ
    -0.07
    éħįç½®æĸ¹éĿ¢
    -0.07
    POSITIVE LOGITS
    .org
    0.07
    åĽºæĢģ
    0.07
     labs
    0.07
    labs
    0.07
    çĶĺ
    0.07
    ujur
    0.06
    licer
    0.06
    enton
    0.06
    åĴķ
    0.06
    tools
    0.06
    Activations Density 0.098%

    No Known Activations