© 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. 31537
    Prev
    Next
    INDEX
    Explanations

    special characters and 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
    zeh
    -0.08
     {{{
    -0.07
    دÙĩ
    -0.07
    abor
    -0.07
    리ìĺ¤
    -0.07
    è¿Ļä¸ĢéĹ®é¢ĺ
    -0.07
    iry
    -0.07
    è¿Ļç§įçݰ象
    -0.06
    鸣
    -0.06
    itzer
    -0.06
    POSITIVE LOGITS
    æĸ¯åŁº
    0.08
    éĩijåĪ¸
    0.07
    gak
    0.07
    姿
    0.07
    ewise
    0.07
    对åįİ
    0.07
    æļĩ
    0.06
    Updater
    0.06
    èĭ±æĸĩåIJįåŃĹ
    0.06
    Bron
    0.06
    Activations Density 0.009%

    No Known Activations