© 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. 26991
    Prev
    Next
    INDEX
    Explanations

    quarter circle exclusive Kwanza

    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
    åħ³æ³¨æĪij
    -0.07
    peg
    -0.07
    Ø®ÙĪا
    -0.07
    大éħĴåºĹ
    -0.06
    大水
    -0.06
    æĿŁ
    -0.06
    payload
    -0.06
    /local
    -0.06
    sov
    -0.06
    大æľīåı¯ä¸º
    -0.06
    POSITIVE LOGITS
    idy
    0.07
    quette
    0.07
     getById
    0.06
    ç»ĻåĪ«äºº
    0.06
    ä¸Ģ亮
    0.06
    ä¸ĢåĪ°
    0.06
    ottes
    0.06
    çĶµåĬĽç³»ç»Ł
    0.06
     apis
    0.06
    请åIJĮåѦ们
    0.06
    Activations Density 0.002%

    No Known Activations