© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 22410
    Prev
    Next
    INDEX
    Explanations

    analysis of factors and results

    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
    Not in Any Lists

    No Comments

    Negative Logits
    Öģ
    -0.07
    æĦıæĥ³ä¸įåĪ°çļĦ
    -0.07
    ÑĤии
    -0.06
    Ùĭ
    -0.06
    æĦıæĥ³ä¸įåĪ°
    -0.06
    ä¸Ģéĥ¨åĪĨ
    -0.06
    人被
    -0.06
    ä¸Ķ
    -0.06
     unimagin
    -0.06
    شارة
    -0.06
    POSITIVE LOGITS
    æĥħåĨµåIJİ
    0.16
    æĺ¯åIJ¦æľī
    0.14
    æĺ¯åIJ¦åŃĺåľ¨
    0.14
    æĺ¯åIJ¦åľ¨
    0.13
    æĺ¯åIJ¦æĺ¯
    0.13
    æĺ¯åIJ¦ä¼ļ
    0.13
    æĺ¯åIJ¦ä¸º
    0.12
    æĺ¯åIJ¦ç¬¦åIJĪ
    0.12
    æĺ¯åIJ¦ä¸İ
    0.12
    éĹ®é¢ĺæŶ
    0.12
    Activations Density 0.652%

    No Known Activations