© 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. 2786
    Prev
    Next
    INDEX
    Explanations

    code and technical terms

    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
     (![
    -0.26
    .MM
    -0.22
    -Trump
    -0.22
    urnished
    -0.22
    ouston
    -0.22
    *))
    -0.21
    ancock
    -0.21
    zego
    -0.21
    SystemService
    -0.20
    "",↵
    -0.20
    POSITIVE LOGITS
    ÃŃsticas
    0.22
    ashtra
    0.20
    ancellable
    0.19
    ascade
    0.19
     GANG
    0.19
    è¸Ķ
    0.19
     helf
    0.19
    agedList
    0.18
     desar
    0.18
    reation
    0.18
    Activations Density 3.403%

    No Known Activations