© 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. 4744
    Prev
    Next
    INDEX
    Explanations

    comparison of alike things

    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
    raca
    -0.07
    oby
    -0.07
    ÏģιÏĥ
    -0.07
    åIJĦ项
    -0.07
    ofi
    -0.06
    æĶ¾å¿ĥ
    -0.06
    зÑĭ
    -0.06
    éĻįèIJ½
    -0.06
    angnya
    -0.06
    ãģĵãģĿ
    -0.06
    POSITIVE LOGITS
    大ä½ĵ
    0.09
    _OWNER
    0.08
    大èĩ´
    0.08
    mt
    0.08
    åIJĮ樣
    0.08
    åIJĮæł·æĺ¯
    0.08
    大åĪĩãģª
    0.07
    åIJĮæł·
    0.07
    머ëĭĪ
    0.07
    ult
    0.07
    Activations Density 0.136%

    No Known Activations