© 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. 34869
    Prev
    Next
    INDEX
    Explanations

    .controller-row or .app or senior

    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
    人马
    -0.06
    abat
    -0.06
    å°±åı«
    -0.06
    .tap
    -0.06
    gn
    -0.06
    ibo
    -0.06
    esign
    -0.06
    odon
    -0.06
    qp
    -0.06
     TBD
    -0.06
    POSITIVE LOGITS
    åħīæĺ¯
    0.07
     lap
    0.07
    ï¼Ŀï¼Ŀï¼Ŀï¼Ŀ
    0.07
    DMIN
    0.07
    æij©æ´Ľ
    0.07
     Coch
    0.07
     Ú©ÙĨ
    0.07
     strÄĥ
    0.06
    æĴ°ç¨¿
    0.06
    emean
    0.06
    Activations Density 0.009%

    No Known Activations