© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen2.5-7B-IT
    5. 20-MATRYOSHKA-65K
    7. 3559
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    "path
    -0.23
    (IOException
    -0.23
    .AddSingleton
    -0.21
    滥
    -0.20
    çļĦçłĶ究
    -0.19
    ())/
    -0.19
    çĸı
    -0.19
    ä»Ļå¢ĥ
    -0.19
    petto
    -0.19
     mark
    -0.18
    POSITIVE LOGITS
    ernaut
    0.20
    illisecond
    0.20
    .dtp
    0.20
    æĥľ
    0.20
    piring
    0.20
    unnable
    0.20
    uars
    0.19
    -Star
    0.19
     consulate
    0.19
    .dateTimePicker
    0.19
    Activations Density 0.001%

    No Known Activations