© 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. 56089
    Prev
    Next
    INDEX
    Explanations

    officer, writer, seat, contacts, Wave, Castleton, primavera, Information, producer

    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
    žd
    -0.08
    kania
    -0.08
     ‘’
    -0.07
    å°±æĺ¯è¿Ļ个
    -0.07
    apel
    -0.07
    uffer
    -0.07
    venus
    -0.07
    zeti
    -0.07
     ÑĦакÑĤиÑĩеÑģки
    -0.07
    azin
    -0.07
    POSITIVE LOGITS
    æĹłè®ºæĺ¯åľ¨
    0.09
    æŁIJç§į
    0.08
    åľ¨æŁIJäºĽ
    0.08
    æĮĩçļĦæĺ¯
    0.07
    æŁIJ个
    0.07
    åľ¨æŁIJ
    0.07
    éĢłåı¥
    0.07
    æīĢæĮĩ
    0.07
    äºĭçī©çļĦ
    0.07
    æĺ¯æĮĩåľ¨
    0.07
    Activations Density 0.132%

    No Known Activations