© 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. 12975
    Prev
    Next
    INDEX
    Explanations

    semicolons and closing braces

    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®ĮäºĨ
    -0.07
    éĿ¢å¹¿
    -0.07
    undra
    -0.07
    (await
    -0.07
    éģĵè¿ľ
    -0.07
    ÙĪض
    -0.06
    类似
    -0.06
    צע
    -0.06
    ìĭľíĶ¼
    -0.06
    çļĦ身影
    -0.06
    POSITIVE LOGITS
    uken
    0.09
    为天
    0.08
    ukk
    0.07
    лÑĥб
    0.07
     recomendamos
    0.07
    æĺ¯å¤©
    0.07
    alp
    0.07
    天å¤ĸ
    0.07
     pel
    0.06
     unt
    0.06
    Activations Density 0.335%

    No Known Activations