© 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. 73
    Prev
    Next
    INDEX
    Explanations

    complex texts

    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
    CGSize
    -0.22
    nuts
    -0.20
    Ÿ
    -0.19
    herits
    -0.19
    èĭ¡
    -0.19
    ::.
    -0.19
     derp
    -0.18
    ibre
    -0.18
    UITableViewCell
    -0.18
    ви
    -0.18
    POSITIVE LOGITS
    .repaint
    0.23
    webtoken
    0.22
    liÄŁini
    0.21
    leftJoin
    0.20
    ç§ijçłĶéĻ¢
    0.20
    avax
    0.20
    éĢ¸
    0.20
    马æĭī
    0.20
    liÄŁ
    0.20
    вÑĪий
    0.20
    Activations Density 0.002%

    No Known Activations