© 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. 1494
    Prev
    Next
    INDEX
    Explanations

    business and IT roles

    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
     Interracial
    -0.47
    ,application
    -0.40
     Wroc
    -0.35
    /INFO
    -0.33
     Millenn
    -0.31
     Erotic
    -0.31
     Stamina
    -0.30
    .CustomButton
    -0.30
    [".
    -0.30
     fkk
    -0.29
    POSITIVE LOGITS
    家éĥ½çŁ¥éģĵ
    0.30
     ofApp
    0.30
     imgUrl
    0.30
     annonces
    0.30
     sublicense
    0.29
     usern
    0.28
    ä½»
    0.28
     sublic
    0.28
     subparagraph
    0.28
     setHidden
    0.28
    Activations Density 8.605%

    No Known Activations