© 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
    2. Qwen3.5-9B Base
    3. 15-QWENSCOPE-RES-64K
    4. 26104
    Prev
    Next
    INDEX
    Explanations

    specific word questions

    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
    æĺ¯ä¸įå¤ŁçļĦ
    -0.08
     apapun
    -0.08
    çļĦåΰæĿ¥
    -0.08
    æĺ¯éĿŀ常éĩįè¦ģçļĦ
    -0.07
    ئÙĥ
    -0.07
    æĤ¨å½ĵåīįçļĦä½įç½®
    -0.07
    åΰæĿ¥çļĦ
    -0.07
    åĩºä¼ļ
    -0.07
    byt
    -0.07
    æľīä¸Ģå®ļ
    -0.07
    POSITIVE LOGITS
    对äºİè¿Ļ个
    0.09
     geweest
    0.08
     بÙħثابة
    0.08
    åĽłç´łå½±åĵį
    0.08
     gewesen
    0.08
     باÙĦÙĨسبة
    0.08
     gonna
    0.08
    对äºİè¿ĻäºĽ
    0.07
     blevet
    0.07
     equivalent
    0.07
    Activations Density 0.159%

    No Known Activations