© 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. 38786
    Prev
    Next
    INDEX
    Explanations

    profession or role

    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
    æĽ´åĬłå¼º
    -0.08
    è®°å¿ĨçĬ¹
    -0.08
    ä¸įæ¯Ķ
    -0.08
    æ¯ıä¸Ģ件
    -0.07
    æĺ¯ä¸Ģæł·çļĦ
    -0.07
    epe
    -0.07
    æĪijæĽ´
    -0.07
    åĴĮåIJĮäºĭ
    -0.07
    .Never
    -0.07
     anyway
    -0.07
    POSITIVE LOGITS
    ä¸ĭéĿ¢æĺ¯å°ıç¼ĸ
    0.08
    以åıĬ
    0.07
    ãģĬãĤĪãģ³
    0.07
    åıĬãģ³
    0.07
     [[
    0.06
     ↵ ↵
    0.06
     mainly
    0.06
     ÙĪØ°ÙĦÙĥ
    0.06
     chiefly
    0.06
     notable
    0.06
    Activations Density 3.055%

    No Known Activations