© 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. 44747
    Prev
    Next
    INDEX
    Explanations

    list formatting and special characters

    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
    es
    -0.07
    up
    -0.06
    ess
    -0.06
    ä¸įä¸Ĭ
    -0.06
    1
    -0.06
    ys
    -0.06
    è¦ģä¸į
    -0.05
    è·Į
    -0.05
     garn
    -0.05
    reh
    -0.05
    POSITIVE LOGITS
    اÙĨات
    0.09
    :list
    0.09
    naval
    0.08
    ä¹ĿæĪIJ
    0.08
    åıĪ大
    0.08
    åıĬæŶæİĮæı¡
    0.08
    ä¸Ĭè¡Ĺ
    0.08
    è¿ĶåĽŀåĪĹ表
    0.08
    IDO
    0.08
    æĽ´ä¸Ĭä¸Ģå±Ĥ楼
    0.08
    Activations Density 0.017%

    No Known Activations