© 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. 1102
    Prev
    Next
    INDEX
    Explanations

    health and science

    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
     pestic
    -0.30
     oppon
    -0.29
     antibiot
    -0.29
     libertin
    -0.29
     consc
    -0.28
    ç½ijé¦ĸ页
    -0.28
     facult
    -0.27
     mastur
    -0.27
     controvers
    -0.26
     indispens
    -0.26
    POSITIVE LOGITS
    æį¢åı¥è¯Ŀ
    0.39
    <path
    0.28
    /XMLSchema
    0.26
    <tag
    0.23
    <source
    0.23
    .mybatisplus
    0.23
    }elseif
    0.23
    .twig
    0.23
    对çħ§æ£ĢæŁ¥
    0.23
    //"
    0.22
    Activations Density 85.925%

    No Known Activations