© 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. 59760
    Prev
    Next
    INDEX
    Explanations

    in advance

    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
    以
    -0.07
    éĴ¦
    -0.07
    ê¸Ģ
    -0.07
    åįĵ
    -0.07
    izza
    -0.07
    astes
    -0.07
    ieber
    -0.07
    çŤ
    -0.07
    pires
    -0.07
    çŀ»
    -0.07
    POSITIVE LOGITS
     Lastly
    0.09
    Lastly
    0.09
    èĮĥåĽ´åĴĮ
    0.07
    严äºİ
    0.07
    令åĴĮ
    0.07
    人æĿ¥
    0.07
    udu
    0.07
    usage
    0.07
    ëŀĺ
    0.07
    äºĨåĽŀæĿ¥
    0.07
    Activations Density 0.001%

    No Known Activations