© 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. 2498
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
     userEmail
    -0.21
     userDetails
    -0.20
     fe
    -0.20
    }.${
    -0.20
    pherd
    -0.19
    Fant
    -0.19
    çľ
    -0.19
    .sul
    -0.19
     impl
    -0.19
    ä»ħä¾Ľ
    -0.18
    POSITIVE LOGITS
    reffen
    0.21
    orias
    0.20
     andre
    0.20
    RectTransform
    0.20
    dition
    0.19
    essor
    0.19
    ListModel
    0.19
     íĨµíķĺìŬ
    0.19
    alus
    0.19
    xfff
    0.19
    Activations Density 0.002%

    No Known Activations