© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 60062
    Prev
    Next
    INDEX
    Explanations

    "via" followed by a method or service

    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
    nya
    -0.10
    zelt
    -0.08
    timeofday
    -0.08
    à¸Ļำ
    -0.08
    à¸ĩ
    -0.08
    andalone
    -0.08
    nds
    -0.07
    uvi
    -0.07
    æĶ¾çŁ¢
    -0.07
    æĥħåĨµä¸ĭ
    -0.07
    POSITIVE LOGITS
    à¥ĩ
    0.10
    /from
    0.09
    heen
    0.09
    以ä¸ĭæĸ¹å¼ı
    0.09
    ลฯ
    0.08
    cling
    0.08
    даÑİÑĤ
    0.08
    fore
    0.08
    /down
    0.08
    ä¸Ģæĸij
    0.08
    Activations Density 0.028%

    No Known Activations