© 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. 812
    Prev
    Next
    INDEX
    Explanations

    prime factorization

    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
    :numel
    -0.26
    erosis
    -0.23
    åķ»
    -0.23
    åħ³äºİæĪij们
    -0.23
    oriously
    -0.23
    âľĹ
    -0.23
     metic
    -0.23
    /Graphics
    -0.23
    eldom
    -0.22
    stitución
    -0.22
    POSITIVE LOGITS
     -:
    0.24
    (SELECT
    0.20
    uards
    0.19
    bellion
    0.19
    acro
    0.19
    éĴ¢æĿIJ
    0.19
    neath
    0.19
    nonnull
    0.18
    FC
    0.18
    åıªçŁ¥éģĵ
    0.18
    Activations Density 0.100%

    No Known Activations