© 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. 1839
    Prev
    Next
    INDEX
    Explanations

    ,

    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
     Clintons
    -0.44
     scaleX
    -0.44
     scaleY
    -0.38
     imageData
    -0.37
     erotica
    -0.36
     imageURL
    -0.36
     tileSize
    -0.36
     difficoltÃł
    -0.34
     imgUrl
    -0.34
     imageSize
    -0.33
    POSITIVE LOGITS
     airstrikes
    0.34
     pornstar
    0.33
     tatto
    0.30
    inerary
    0.29
     cornerback
    0.29
     Girlfriend
    0.29
     SHIPPING
    0.28
     erotico
    0.28
     STREET
    0.28
     interceptions
    0.28
    Activations Density 6.052%

    No Known Activations