© 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. 1278
    Prev
    Next
    INDEX
    Explanations

    technical or specific phrases

    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
    detalle
    -0.22
    GBT
    -0.21
    .btnDelete
    -0.20
    archs
    -0.20
     Glen
    -0.20
    BuilderInterface
    -0.20
    stroy
    -0.20
    ModelProperty
    -0.19
     desar
    -0.19
    ventus
    -0.19
    POSITIVE LOGITS
    ethereum
    0.23
    èħĻ
    0.21
    quin
    0.21
    clusão
    0.21
     Lyon
    0.20
    .wr
    0.20
    дÑĢеÑģ
    0.19
    felt
    0.19
    uguay
    0.19
    责任人
    0.19
    Activations Density 0.009%

    No Known Activations