© 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. 37675
    Prev
    Next
    INDEX
    Explanations

    attribute descriptions

    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
    çĥŃéŨæĸĩç«ł
    -0.07
    ople
    -0.07
    jin
    -0.07
    æĪIJåIJį
    -0.07
    æĢĴ
    -0.07
    intree
    -0.07
    åī²
    -0.07
    engt
    -0.07
    çļĦåIJįä¹ī
    -0.07
    .symbol
    -0.07
    POSITIVE LOGITS
    éĺIJè¿°
    0.08
    à¸ĸ
    0.08
    çŁŃçļĦ
    0.08
    æııè¿°
    0.08
    description
    0.07
    .gs
    0.07
     Gecko
    0.07
     Longer
    0.07
     longer
    0.07
    丽èİİ
    0.07
    Activations Density 0.224%

    No Known Activations