© 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
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 30762
    Prev
    Next
    INDEX
    Explanations

    earth, Town, won, etic

    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
    æĿ¥æĬĵ
    -0.07
     ram
    -0.07
     promot
    -0.07
    ä¸įè´Ł
    -0.07
    ä¸įåĪ©
    -0.07
    émat
    -0.06
    ibles
    -0.06
    æįī
    -0.06
     stron
    -0.06
    mmm
    -0.06
    POSITIVE LOGITS
    spur
    0.08
    åĩij
    0.08
    æĺı
    0.07
    çļİ
    0.07
    ulis
    0.07
    [Math
    0.07
    åĩīæ°´
    0.07
    éĢĴ
    0.07
    arendra
    0.07
    gues
    0.07
    Activations Density 0.017%

    No Known Activations