© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 59964
    Prev
    Next
    INDEX
    Explanations

    assembly attributes or code blocks

    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
    Negative Logits
    人说
    -0.08
    çļĦäººä¹Ł
    -0.08
    erio
    -0.07
    人ãĤĤ
    -0.07
    ogia
    -0.07
    esimo
    -0.07
    人æĿ¥è¯´
    -0.07
     Ú©ÙĨÙĨد
    -0.07
    æĻĵ
    -0.07
    æīįåı¯
    -0.07
    POSITIVE LOGITS
    <|box_end|>
    0.07
    ¼
    0.07
    俱ä¹IJéĥ¨
    0.06
    Ħ
    0.06
    ragt
    0.06
    á»Ŀ
    0.06
    irty
    0.06
    èģĶéĺ²èģĶæݧ
    0.06
     embod
    0.06
    ä¸įåı¯æĢĿè®®
    0.06
    Activations Density 0.003%

    No Known Activations