© 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. 32813
    Prev
    Next
    INDEX
    Explanations

    football clubs and institutions

    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
     УÑĢалÑĮ
    -0.09
    inkle
    -0.09
    è¿Ľåİ»
    -0.09
    说起æĿ¥
    -0.09
     ÐIJлÑĤай
    -0.09
     Indonesian
    -0.08
    èį·èĺŃ
    -0.08
    é¡·
    -0.08
     Malaysian
    -0.08
     boliv
    -0.08
    POSITIVE LOGITS
    ä½įäºİ
    0.10
    çģ¾åĮº
    0.08
    ä½įæĸ¼
    0.08
     at
    0.07
     Friendship
    0.07
    ä½ķåľ°
    0.07
    ä»Ļ女
    0.07
    æ´»åĬ¨åľ°çĤ¹
    0.07
    ä¸Ńå¿ĥåŁİå¸Ĥ
    0.07
    æīĢåľ¨åŁİå¸Ĥ
    0.07
    Activations Density 1.293%

    No Known Activations