© 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. 814
    Prev
    Next
    INDEX
    Explanations

    punctuation and symbols

    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
    /Dk
    -0.65
    :<?
    -0.48
    åĭł
    -0.48
    -With
    -0.47
    )./
    -0.47
    "<?
    -0.46
    :';↵
    -0.45
    :'.$
    -0.44
    :".$
    -0.44
    MMdd
    -0.42
    POSITIVE LOGITS
    /
    0.37
    (
    0.32
    [
    0.32
    -
    0.30
    ↵
    0.29
    $
    0.29
    _
    0.29
    '
    0.28
    "
    0.27
    *
    0.27
    Activations Density 8.978%

    No Known Activations