© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen2.5-7B-IT
    5. 20-MATRYOSHKA-65K
    7. 2003
    Prev
    Next
    INDEX
    Explanations

    medical procedures

    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
    roupon
    -0.28
    onDelete
    -0.27
    æĸ°æµªè´¢ç»ı
    -0.26
    :animated
    -0.26
    idente
    -0.25
    /animate
    -0.25
    orgeous
    -0.22
    parator
    -0.22
    vider
    -0.22
    NullPointerException
    -0.22
    POSITIVE LOGITS
     viá»ĩc
    0.29
    çļĦåĪ°æĿ¥
    0.25
    ä»»ä½ķå½¢å¼ı
    0.24
    ä¸įå¿ħè¦ģçļĦ
    0.24
    建设åĴĮ
    0.24
    æ¯ıä¸Ģ次
    0.24
    çļ²
    0.24
    à¸ģาร
    0.24
     use
    0.23
    ãģ§ãģ®
    0.22
    Activations Density 7.784%

    No Known Activations