© 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. 10766
    Prev
    Next
    INDEX
    Explanations

    X-Men, classic, iconic

    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
    ä¸įæĺİ
    -0.09
     reportedly
    -0.08
    ç«Ł
    -0.07
    ç«Łæĺ¯
    -0.07
     guessed
    -0.07
    dif
    -0.07
    åħ·æľīä¸Ģå®ļ
    -0.07
    eia
    -0.07
    çļĦåı¯èĥ½
    -0.07
    podob
    -0.07
    POSITIVE LOGITS
    æĪij们éĥ½çŁ¥éģĵ
    0.10
    ç»ıåħ¸
    0.10
     famously
    0.10
    ç»ıåħ¸çļĦ
    0.10
     iconic
    0.10
     classic
    0.09
    çļĦç»ıåħ¸
    0.09
     famos
    0.09
     cornerstone
    0.09
     famous
    0.08
    Activations Density 0.301%

    No Known Activations