© 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. 38470
    Prev
    Next
    INDEX
    Explanations

    technical field introduction

    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
    -done
    -0.08
    lado
    -0.08
    leben
    -0.08
    .hl
    -0.08
    æ¯ıä¸ĢåIJį
    -0.08
    ãĥĥãĤ³
    -0.08
    åij¨ä¸ī
    -0.07
     ìĤ¬ìļ©íķĺ기
    -0.07
    æĽ´åħ¨
    -0.07
    imbus
    -0.07
    POSITIVE LOGITS
    æ¸Ŀ
    0.07
    ych
    0.06
    西æĸ¯
    0.06
     synonym
    0.06
     beis
    0.06
    th
    0.06
    çĩĥ
    0.06
    çªģå¦Ĥåħ¶æĿ¥çļĦ
    0.06
    침
    0.05
    ìĬ¹
    0.05
    Activations Density 0.031%

    No Known Activations