© 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. 334
    Prev
    Next
    INDEX
    Explanations

    medical

    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
     therap
    -0.27
     createDate
    -0.26
     yOffset
    -0.26
     acompaña
    -0.26
     gql
    -0.26
     minY
    -0.24
     Sequelize
    -0.23
    berra
    -0.23
    å¹¼ç¨ļ
    -0.22
     xOffset
    -0.22
    POSITIVE LOGITS
    ðŁļ©
    0.35
     treatment
    0.35
     health
    0.31
     treatments
    0.29
     medical
    0.27
     care
    0.27
    "path
    0.27
    raquo
    0.27
    cratch
    0.26
    .openConnection
    0.26
    Activations Density 5.321%

    No Known Activations