© 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. 1016
    Prev
    Next
    INDEX
    Explanations

    various/many

    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
     Jackets
    -0.30
    åı¦å¤ĸä¸Ģ个
    -0.28
    äºĨä¸Ģåı¥
    -0.28
    第äºĮ次
    -0.27
    第ä¸ī次
    -0.27
    åı¦ä¸Ģ个
    -0.26
    åı¦ä¸Ģç§į
    -0.26
    åı¦ä¸Ģä½į
    -0.25
     subparagraph
    -0.25
    è¿ĻæĿ¡è·¯
    -0.25
    POSITIVE LOGITS
     various
    0.66
    åIJĦç§į
    0.57
    ä¸ĢäºĽ
    0.52
    åIJĦ项
    0.50
     many
    0.49
    åIJĦç±»
    0.48
    åIJĦ
    0.47
     Various
    0.46
    åĵªäºĽ
    0.46
    çļĦåIJĦç§į
    0.45
    Activations Density 14.083%

    No Known Activations