© 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. 20845
    Prev
    Next
    INDEX
    Explanations

    SERVICE, parameter, activity, message, Text

    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
    irm
    -0.09
    eking
    -0.08
    ä¹Łä¸įä¾ĭå¤ĸ
    -0.08
    æľĢæĸ°ç«łèĬĤ
    -0.07
    æĽ¾çĶ¨åIJį
    -0.07
    iene
    -0.07
    ä¹Łæĺ¯å¦ĤæѤ
    -0.07
    оÑģÑĤо
    -0.07
    è¯ŀ
    -0.07
    irlo
    -0.07
    POSITIVE LOGITS
    lf
    0.07
    天ä¹ĭ
    0.07
    ÑĦÑĤа
    0.07
    immat
    0.07
    西
    0.07
    mes
    0.06
    apsed
    0.06
    åŃ¦æľŁçļĦ
    0.06
    hés
    0.06
     ocup
    0.06
    Activations Density 0.019%

    No Known Activations