© 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. 23606
    Prev
    Next
    INDEX
    Explanations

    list separators and "this story"

    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
    à¸ŀัà¸ĩ
    -0.07
    ussi
    -0.07
    åıĺå¾Ĺ
    -0.07
    è´¼
    -0.07
    uff
    -0.07
    azor
    -0.06
    æĹ¢çĦ¶å¦ĤæѤ
    -0.06
    rell
    -0.06
    mond
    -0.06
    亿
    -0.06
    POSITIVE LOGITS
    è¿Ļ两ç§į
    0.08
    å¸ĮæľĽå¯¹å¤§å®¶æľīæīĢ帮åĬ©
    0.08
    çļĦ两个
    0.08
    orthy
    0.08
    èĩ¼
    0.07
    æ·±åıĹ广大
    0.07
    éĩįå¤į
    0.07
    ä¸īçŃī
    0.07
    ORTH
    0.07
     repeated
    0.07
    Activations Density 0.014%

    No Known Activations