© 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. 2059
    Prev
    Next
    INDEX
    Explanations

    table separators

    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
    .InnerException
    -0.24
    âĦī
    -0.23
    ábado
    -0.23
    ","","
    -0.21
    åķ»
    -0.21
     pupper
    -0.21
    кÑĨион
    -0.21
    WAYS
    -0.21
    DMETHOD
    -0.21
     ↵		↵
    -0.20
    POSITIVE LOGITS
    ?↵
    0.36
    !↵
    0.35
    .↵
    0.35
    ;↵
    0.32
     ?↵
    0.32
    )↵
    0.29
    ï¼Ł↵
    0.28
    >.↵
    0.28
    ".↵
    0.27
    ãĢĤ↵
    0.27
    Activations Density 0.157%

    No Known Activations