© 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. 58812
    Prev
    Next
    INDEX
    Explanations

    main class or window

    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
    ä¹ĭæģĭ
    -0.08
    éĩį大æĦıä¹ī
    -0.07
    ertools
    -0.07
    aven
    -0.07
    неÑĤÑĥ
    -0.07
    osz
    -0.07
    å¾Ĺ天çĭ¬
    -0.07
    æŃ¤åľ°
    -0.07
    鹦
    -0.07
    çĥŁéħĴ
    -0.07
    POSITIVE LOGITS
    è¿ĩç¨ĭ
    0.07
     process
    0.07
    ç¯ĩ
    0.07
    ä¸įäºĨäºĨ
    0.07
    ingham
    0.07
    ÙIJØŃ
    0.07
     processes
    0.07
    /main
    0.06
    ĸ
    0.06
    ÛĮرÙĩ
    0.06
    Activations Density 0.009%

    No Known Activations