© 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. 18476
    Prev
    Next
    INDEX
    Explanations

    being busy or occupied

    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
    æĬ±åĽ¢
    -0.07
    ä¸įèIJ½
    -0.07
    çĪ·
    -0.07
    éķ¿æľŁä½¿çĶ¨
    -0.07
    åľ¨ä½¿çĶ¨
    -0.07
    entar
    -0.07
    æľĢåĪĿãģ«
    -0.06
     ì²ĺìĿĮìľ¼ë¡ľ
    -0.06
    æľīç¦ı
    -0.06
    沿çĶ¨
    -0.06
    POSITIVE LOGITS
    æĹłæļĩ
    0.12
    两ä¸į误
    0.12
    å¿Ļ
    0.11
    åĪĨ身
    0.11
    ä¼ĺåħĪ级
    0.11
    å¿Ļç¢Į
    0.11
     busy
    0.11
    ç¹ģå¿Ļ
    0.10
     priorities
    0.10
     báºŃn
    0.10
    Activations Density 0.477%

    No Known Activations