© 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. 19784
    Prev
    Next
    INDEX
    Explanations

    runway open

    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
    ç¼ĵç¼ĵåľ°
    -0.07
    olon
    -0.07
     Hairst
    -0.07
    ä»»ä½ķå½¢å¼ıçļĦ
    -0.07
    ardy
    -0.07
    impi
    -0.07
    µ
    -0.07
    åĵĪçĻ»
    -0.06
    æľīå¿Ĺ
    -0.06
    agraph
    -0.06
    POSITIVE LOGITS
    é¤ĺ
    0.07
    ç¢
    0.07
    fels
    0.07
     ÐłÐ¾ÑģÑģ
    0.07
    etest
    0.07
    ÃįN
    0.07
    Ùĩب
    0.06
    ãĨ
    0.06
    åijĬè¯īä½ł
    0.06
    æĪij们éĥ½çŁ¥éģĵ
    0.06
    Activations Density 0.127%

    No Known Activations