© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen2.5-7B-IT
    5. 20-MATRYOSHKA-65K
    7. 4224
    Prev
    Next
    INDEX
    Explanations

    word parts

    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
    Negative Logits
     Escorts
    -0.29
     sluts
    -0.27
     Patio
    -0.26
     disappe
    -0.25
    ionales
    -0.25
     Pruitt
    -0.25
    GEST
    -0.24
    /Dk
    -0.24
     âĵĺ
    -0.23
     GANG
    -0.23
    POSITIVE LOGITS
     currentPlayer
    0.24
    caffold
    0.23
    -
    0.23
    庵
    0.23
     (
    0.22
    /
    0.22
    ="__
    0.21
     –
    0.20
     hmac
    0.20
    ,{"
    0.20
    Activations Density 0.580%

    No Known Activations