© 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. 60920
    Prev
    Next
    INDEX
    Explanations

    mathematical problems and equations

    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
    å¨ĩ妻
    -0.07
    çݺ
    -0.07
    ëĭ·ì»´
    -0.07
     nachdem
    -0.07
     Bradford
    -0.07
    æĺ¯ä¸Ģ个å¾Ī
    -0.06
    ainty
    -0.06
    å¹´ä¹ĭåIJİ
    -0.06
    åľ°åıijçİ°
    -0.06
    æİ¥æīĭ
    -0.06
    POSITIVE LOGITS
    eluk
    0.07
    ä¸įè´¥
    0.07
    诸
    0.07
    ä¸įçĿĢ
    0.07
    "${
    0.07
    æľĢå¤ļ
    0.07
    ÙĪاب
    0.07
    anoi
    0.07
    æĪijæĦ¿
    0.07
    åĵªäºĽéĹ®é¢ĺ
    0.06
    Activations Density 0.021%

    No Known Activations