© 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. 1458
    Prev
    Next
    INDEX
    Explanations

    numerical and code data

    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
     erotica
    -0.19
     proprietor
    -0.19
    ItemSelected
    -0.18
     åĮ
    -0.18
     cloves
    -0.18
     swirl
    -0.18
     unthinkable
    -0.18
    -
    -0.18
    äºĮåŃĹ
    -0.18
     ejercicio
    -0.18
    POSITIVE LOGITS
    ÐŁÐµÑĤеÑĢбÑĥÑĢг
    0.26
    âĦī
    0.24
     manh
    0.23
    (IOException
    0.21
    .MouseAdapter
    0.21
    twor
    0.21
    į°ìĿ´
    0.21
    *****↵
    0.21
    å¾Ī满æĦı
    0.21
    :numel
    0.20
    Activations Density 0.626%

    No Known Activations