© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 14843
    Prev
    Next
    INDEX
    Explanations

    x users or hours or days

    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°´
    -0.07
    ouw
    -0.07
    çļĦæĺ¯ä»Ģä¹Ī
    -0.07
    æѦç¥ŀ
    -0.07
    å®Ŀé¾Ļ
    -0.07
     somehow
    -0.07
    adden
    -0.07
    ÄĽz
    -0.06
    æĺ¯è°ģ
    -0.06
    tede
    -0.06
    POSITIVE LOGITS
    ç±»åŀĭçļĦ
    0.09
    ulam
    0.09
    Äįan
    0.08
    æł·çļĦ
    0.08
    ä¹ĭå¤ļ
    0.07
    onian
    0.07
    樣çļĦ
    0.07
    locker
    0.07
    ;background
    0.07
    .TYPE
    0.07
    Activations Density 0.037%

    No Known Activations