© 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. 11065
    Prev
    Next
    INDEX
    Explanations

    boolean values or symbols

    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
    诸天
    -0.07
    æľº
    -0.07
    åħ·æľīä¸Ģå®ļçļĦ
    -0.06
    asca
    -0.06
    åIJĦæĸ¹éĿ¢çļĦ
    -0.06
    èĩªç¼ĸ
    -0.06
    onaut
    -0.06
    æ¡ĥ
    -0.06
     ëģĬ
    -0.06
    rott
    -0.06
    POSITIVE LOGITS
    emode
    0.07
    å©¿
    0.07
    Occurred
    0.07
    åį¡è·¯
    0.07
    åħ®åħ®
    0.07
    è¡¥éĴĻ
    0.07
    ä¸ĥéĩĮ
    0.07
    .flip
    0.07
    lash
    0.07
    developers
    0.07
    Activations Density 0.002%

    No Known Activations