© 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. 1963
    Prev
    Next
    INDEX
    Explanations

    common word endings

    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
    ystack
    -0.27
    opleft
    -0.25
    apist
    -0.25
    linky
    -0.25
    ensibly
    -0.25
    placer
    -0.25
    noinspection
    -0.24
    'icon
    -0.24
    aeda
    -0.24
    -cookie
    -0.23
    POSITIVE LOGITS
    ar
    0.29
    in
    0.29
    at
    0.29
    r
    0.29
    im
    0.28
    as
    0.27
    n
    0.27
    am
    0.26
    ic
    0.26
    p
    0.26
    Activations Density 0.254%

    No Known Activations