© 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. 15288
    Prev
    Next
    INDEX
    Explanations

    difference if

    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
    è¿ĶåĽŀ顶éĥ¨
    -0.08
    åıĪéģĵ
    -0.08
    红楼
    -0.08
    ä¸ĭéĿ¢å°±
    -0.08
     Viên
    -0.07
    åĨįä¹Łä¸į
    -0.07
    è¯ĿæĿ¥
    -0.07
    алан
    -0.07
    bur
    -0.07
    ä¸įåħ¥
    -0.07
    POSITIVE LOGITS
    ç¡®å®ŀ
    0.10
     дейÑģÑĤвиÑĤелÑĮно
    0.08
    確實
    0.08
    çļĦç¡®
    0.08
    å½ĵçĦ¶æĺ¯
    0.08
    ãģ¾ãģļ
    0.08
    ç¡®å®ŀæĺ¯
    0.07
     effectivement
    0.07
     tùy
    0.07
    é¦ĸåħĪåľ¨
    0.07
    Activations Density 0.808%

    No Known Activations