© 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. 10334
    Prev
    Next
    INDEX
    Explanations

    nationalities or places

    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
    å¦ĥ
    -0.07
    æ¿Ģ
    -0.07
    ottie
    -0.07
    ž
    -0.06
    گرÛĮ
    -0.06
    æĪijåĽ½
    -0.06
    ä¸įå½±åĵį
    -0.06
    æĪijåĽ½çļĦ
    -0.06
     mera
    -0.06
    æĦļèł¢
    -0.06
    POSITIVE LOGITS
    burgh
    0.09
    -wide
    0.08
    apolis
    0.08
    åıĬ缸åħ³
    0.08
    åıĬåij¨è¾¹
    0.08
    éļ¾æ±Ĥ
    0.08
    -Za
    0.08
    burg
    0.07
    æ³ģ
    0.07
    è·¯éĢı
    0.07
    Activations Density 0.225%

    No Known Activations