© 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. 44715
    Prev
    Next
    INDEX
    Explanations

    the same

    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
    ivet
    -0.07
    lem
    -0.06
    汤
    -0.06
    ç¡®å®ŀæĺ¯
    -0.06
     ro
    -0.06
    åijĺ
    -0.06
    åĤį
    -0.06
     all
    -0.06
    all
    -0.06
    èĪ¬
    -0.06
    POSITIVE LOGITS
    åIJĮä¸Ģ个
    0.10
     tadi
    0.10
    åIJĮä¸Ģ
    0.09
    åľ¨åIJĮä¸Ģ
    0.09
    æĹ©äºĽ
    0.09
    estan
    0.09
    åIJĮãģĺ
    0.08
    ptica
    0.08
    åIJĮæł·çļĦ
    0.08
     aynı
    0.08
    Activations Density 0.105%

    No Known Activations