© 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. 727
    Prev
    Next
    INDEX
    Explanations

    To or About

    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
    azia
    -0.08
    koord
    -0.08
    preter
    -0.08
    _via
    -0.07
    á»ıa
    -0.07
    ellit
    -0.07
    .VERSION
    -0.07
     gelt
    -0.07
     zufolge
    -0.07
    ä¸įåIJĮæŶ
    -0.07
    POSITIVE LOGITS
    åĪ¨
    0.07
    .predict
    0.07
    _nc
    0.07
    婺
    0.07
    Æ°a
    0.07
    rl
    0.06
    uil
    0.06
    æĩ¦
    0.06
    çIJĨçļĦ
    0.06
    ä¸įçIJĨ
    0.06
    Activations Density 0.001%

    No Known Activations