© 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. 1902
    Prev
    Next
    INDEX
    Explanations

    technical/medical terms

    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
    ".
    -0.23
    .
    -0.22
    ."
    -0.22
    ().
    -0.22
    __.
    -0.21
    []){↵
    -0.21
     {}.
    -0.21
    ãĢĤ
    -0.20
    .'
    -0.20
    '.
    -0.20
    POSITIVE LOGITS
    ãĢģ
    0.47
    -,
    0.39
    ãĢģ“
    0.38
    ï¼īãĢģ
    0.38
     (),
    0.36
    ãĢįãĢĮ
    0.36
    (),
    0.34
    ?,
    0.34
     ?,
    0.33
     [],
    0.32
    Activations Density 7.044%

    No Known Activations