© 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. 1025
    Prev
    Next
    INDEX
    Explanations

    peripheral

    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
     the
    -0.31
     a
    -0.30
     our
    -0.26
     these
    -0.25
     any
    -0.25
     those
    -0.25
     their
    -0.24
     an
    -0.24
     licensors
    -0.24
     your
    -0.23
    POSITIVE LOGITS
    ;]/
    0.31
    "<?
    0.29
    aeper
    0.28
    *sp
    0.28
    "';
    0.28
    :animated
    0.27
    "struct
    0.26
    建档ç«ĭ
    0.26
     {{--<
    0.26
    põe
    0.25
    Activations Density 0.346%

    No Known Activations