© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen2.5-7B-IT
    5. 20-MATRYOSHKA-65K
    7. 1013
    Prev
    Next
    INDEX
    Explanations

    say "the"

    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
    -Trump
    -0.36
    -ves
    -0.31
    转载请
    -0.29
     beÄŁen
    -0.28
    注æĺİæĿ¥æºIJ
    -0.28
    |array
    -0.26
     Casinos
    -0.26
     {?>↵
    -0.25
    çīĪæĿĥå½Ĵ
    -0.25
    :UITableView
    -0.24
    POSITIVE LOGITS
     the
    0.79
    the
    0.55
    	the
    0.44
     The
    0.43
    _the
    0.41
    .the
    0.39
     our
    0.36
    The
    0.36
    ,the
    0.35
     their
    0.34
    Activations Density 8.174%

    No Known Activations