© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen2.5-7B-IT
    5. 20-MATRYOSHKA-65K
    7. 698
    Prev
    Next
    INDEX
    Explanations

    programming code

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    chanind/qwen2.5-7B-it-layer-20-saes/pile/matryoshka/k-100
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ä¸ĭéĿ¢æĺ¯å°ı
    -0.30
    .PerformLayout
    -0.26
    主ä¹īæĢĿæĥ³
    -0.26
    ĭ
    -0.26
    èĩªçĦ¶èĢĮ
    -0.24
    åĬĽè¿ĺæĺ¯
    -0.24
    ä½Ĩä¸įéĻIJ
    -0.24
    åŬ
    -0.24
    ,exports
    -0.23
     lastIndex
    -0.23
    POSITIVE LOGITS
    è¿ĶåĽŀæIJľçĭIJ
    0.33
    ?"↵↵↵↵
    0.31
    /Dk
    0.29
    çķĮ第ä¸Ģ
    0.28
    rbrace
    0.28
    并ä¸įæĦıåij³
    0.28
     ohio
    0.27
    unitOfWork
    0.27
     -------------------------------------------------------------------------
    0.27
    /WebAPI
    0.26
    Activations Density 7.224%

    No Known Activations