© 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. 1180
    Prev
    Next
    INDEX
    Explanations

    specific references

    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
    ;]/
    -0.24
    >(*
    -0.24
    .RELATED
    -0.23
    lish
    -0.23
    ;/*
    -0.23
    åİŁæĸĩåľ°åĿĢ
    -0.23
    -Semit
    -0.22
    .HttpServlet
    -0.22
    .intValue
    -0.22
    Ū
    -0.22
    POSITIVE LOGITS
    -Javadoc
    0.25
     '"';↵
    0.24
     ".";↵
    0.23
     "'";↵
    0.22
     arbe
    0.21
     vej
    0.20
     ['',
    0.20
    IndexChanged
    0.19
     %"
    0.19
    èĴ¡
    0.19
    Activations Density 1.070%

    No Known Activations