© 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. 243
    Prev
    Next
    INDEX
    Explanations

    dates and archives

    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
    ¡´
    -0.23
    efs
    -0.22
    ivec
    -0.21
    xFFFFFF
    -0.21
    .handleSubmit
    -0.21
    \API
    -0.20
     desi
    -0.20
     søger
    -0.20
     disappe
    -0.20
    å§Ĭ
    -0.20
    POSITIVE LOGITS
    女æĢ§æľĭåıĭ
    0.21
    jsonData
    0.20
    evity
    0.20
    çļĦå½¢å¼ı
    0.19
    heritance
    0.19
    å½¢å¼ı
    0.18
     Synopsis
    0.18
    çŃīå½¢å¼ı
    0.18
    /gin
    0.18
    .sax
    0.18
    Activations Density 0.189%

    No Known Activations