© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen2.5-7B-IT
    5. 20-MATRYOSHKA-65K
    7. 3542
    Prev
    Next
    INDEX
    Explanations

    numbers

    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
    ä¸ĢåĪĢ
    -0.23
    paque
    -0.21
    entine
    -0.21
    /inet
    -0.21
    =\"%
    -0.20
    isible
    -0.20
    nection
    -0.19
    ðŁļ©
    -0.19
    categorie
    -0.19
    /repos
    -0.19
    POSITIVE LOGITS
    addock
    0.21
    çŁį
    0.21
    cação
    0.20
    anical
    0.20
    itures
    0.19
    scrição
    0.19
    å©¿
    0.18
    mong
    0.18
    wró
    0.18
    .shell
    0.18
    Activations Density 0.091%

    No Known Activations