© 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. 3667
    Prev
    Next
    INDEX
    Explanations

    position or number

    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
    :both
    -0.24
    both
    -0.23
    è¿Ļ两ç§į
    -0.23
     both
    -0.23
    éĥ¨åī¯
    -0.23
    htdocs
    -0.22
     Both
    -0.22
    .forChild
    -0.22
    Both
    -0.21
    EmptyEntries
    -0.21
    POSITIVE LOGITS
    æľĢåIJİä¸Ģ个
    0.47
    第ä¸Ģ个
    0.42
     last
    0.42
     first
    0.41
    æľĢåIJİä¸Ģ
    0.40
    é¦ĸ个
    0.39
    æľĢ
    0.38
    çļĦ第ä¸Ģ个
    0.37
    ä¸ŃæľĢ
    0.37
    第ä¸ĢåIJį
    0.36
    Activations Density 0.715%

    No Known Activations