© 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. 3459
    Prev
    Next
    INDEX
    Explanations

    scientific text

    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
    èıħ
    -0.20
    ÙħÙĪÙĤع
    -0.20
    éĮ
    -0.20
    éĨĭ
    -0.19
    CGSize
    -0.19
    çľ·
    -0.18
    æī®
    -0.18
     ìľĦíķĺìŬ
    -0.18
    filesize
    -0.17
     noqa
    -0.17
    POSITIVE LOGITS
    ystack
    0.23
    isoft
    0.23
    impse
    0.22
    ogenerated
    0.22
    libft
    0.22
    endencies
    0.22
    alleries
    0.21
    ermen
    0.21
    صÙĨد
    0.21
    herits
    0.21
    Activations Density 0.001%

    No Known Activations