© 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. 1975
    Prev
    Next
    INDEX
    Explanations

    say "that"

    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
    onents
    -0.25
    {/*
    -0.25
    :numel
    -0.22
    grily
    -0.22
     addslashes
    -0.21
    imulator
    -0.21
     stripslashes
    -0.20
    referer
    -0.20
    swers
    -0.20
    memberof
    -0.20
    POSITIVE LOGITS
     that
    0.65
     rằng
    0.63
     bahwa
    0.62
    that
    0.60
    _that
    0.46
     Ø£ÙĨ
    0.43
    	that
    0.43
     dass
    0.41
     ÑĩÑĤо
    0.36
     que
    0.35
    Activations Density 2.561%

    No Known Activations