© 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. Qwen2.5-7B-IT
    5. 20-MATRYOSHKA-65K
    7. 3936
    Prev
    Next
    INDEX
    Explanations

    technical or code snippets

    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
    acists
    -0.23
     _______,
    -0.22
    mensagem
    -0.22
     :";↵
    -0.21
    åŁĭ
    -0.20
    >Show
    -0.20
    foundland
    -0.20
    ÑĦеÑģÑģиона
    -0.20
    ARSER
    -0.20
    buat
    -0.20
    POSITIVE LOGITS
    æĢ§ä»·
    0.21
    uhan
    0.19
    èĢĮåIJİ
    0.19
     aVar
    0.18
    PerPixel
    0.18
     cuer
    0.18
    æ»ĭ
    0.18
    åļ¯
    0.17
    éĵ³
    0.17
    IJèĹı
    0.17
    Activations Density 0.002%

    No Known Activations