© 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. 4696
    Prev
    Next
    INDEX
    Explanations

    not suggesting improvement

    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
    æĹłè®ºä»İ
    -0.09
    ovas
    -0.08
    æĹłè®ºæĺ¯
    -0.08
    æĹłè®ºåľ¨
    -0.08
    ä»»ä½ķå½¢å¼ıçļĦ
    -0.08
    æĹłè®ºæĺ¯åľ¨
    -0.08
    лаг
    -0.08
     taas
    -0.07
    ĵ¨
    -0.07
     accordingly
    -0.07
    POSITIVE LOGITS
    ä½Ĩèĩ³å°ij
    0.17
     exact
    0.12
    ä½Ĩåı¯ä»¥
    0.11
    ãģ¾ãģĽãĤĵãģĮ
    0.11
    Exact
    0.10
    exact
    0.10
     Exact
    0.10
     outright
    0.10
    ä½Ĩæľī
    0.10
     but
    0.09
    Activations Density 0.249%

    No Known Activations