© 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. 2864
    Prev
    Next
    INDEX
    Explanations

    code and math

    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
    mercial
    -0.28
    Hotéis
    -0.28
    icensing
    -0.27
     Decompiled
    -0.25
    );\↵
    -0.25
    tingham
    -0.25
    aterangepicker
    -0.24
    traîn
    -0.24
    oriously
    -0.24
    ourcem
    -0.24
    POSITIVE LOGITS
    ожеÑĤ
    0.20
    ç©¿ä¸Ĭ
    0.20
    稳妥
    0.19
    æĻı
    0.19
    иÑĢÑĥеÑĤÑģÑı
    0.19
    U
    0.18
    O
    0.18
    _sold
    0.18
     gridColumn
    0.17
     stal
    0.17
    Activations Density 0.358%

    No Known Activations