© 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. 52069
    Prev
    Next
    INDEX
    Explanations

    geographical names and code syntax

    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
    åħ¬åı¸æĢ§è´¨
    -0.07
    ãģķãģĦ
    -0.07
    æĺ¯ä¸Ģç§įéĿŀ常
    -0.06
    gern
    -0.06
    abah
    -0.06
    çļĦ好åĿı
    -0.06
    quine
    -0.06
    tese
    -0.06
    ä½Ļ家
    -0.06
    arani
    -0.06
    POSITIVE LOGITS
    ä¸Ģä½ľ
    0.08
     afford
    0.07
    æĢĴæĶ¾
    0.07
    èµ°å¾Ĺ
    0.07
    ĸ
    0.07
     geschafft
    0.07
    ç¥IJ
    0.07
    帮大家
    0.07
    åİ»ä½ķ
    0.07
    .findByIdAndUpdate
    0.07
    Activations Density 0.021%

    No Known Activations