© 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. 561
    Prev
    Next
    INDEX
    Explanations

    code and programming

    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
    ancock
    -0.29
    yclopedia
    -0.28
    outu
    -0.27
    ripple
    -0.27
    ordial
    -0.27
    rary
    -0.25
    izzer
    -0.25
    grily
    -0.24
    izzas
    -0.23
    venes
    -0.23
    POSITIVE LOGITS
    avanaugh
    0.51
    incinn
    0.47
    æĹłè®ºæĺ¯åħ¶
    0.29
    berra
    0.29
    ISTRIBUT
    0.28
    åIJįåĪĹåīį
    0.28
    ackbar
    0.28
    REFIX
    0.27
    .AutoComplete
    0.27
    aukee
    0.27
    Activations Density 7.233%

    No Known Activations