© 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. 40312
    Prev
    Next
    INDEX
    Explanations

    mathematical expressions with $

    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
    åı«ä»Ģä¹Ī
    -0.07
    -turned
    -0.07
    .named
    -0.07
    ìĤ´
    -0.07
    è·¯éĢı
    -0.07
    æ±Ľ
    -0.07
    åºĶåħ·å¤ĩ
    -0.07
    ppv
    -0.07
    èĭ±æĸĩåIJį称
    -0.07
    ensored
    -0.07
    POSITIVE LOGITS
    ä¸Ķ
    0.10
    表æĺİ
    0.08
    atul
    0.08
    æĦıåij³çĿĢ
    0.08
    ogu
    0.07
    ä¹Łå°±æĦıåij³çĿĢ
    0.07
    ĥ
    0.07
    ä¸īéĿ¢
    0.07
    æݥ踵
    0.07
    à¤ļà¥įà¤Ľ
    0.07
    Activations Density 0.023%

    No Known Activations