© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen2.5-7B-IT
    5. 20-MATRYOSHKA-65K
    7. 716
    Prev
    Next
    INDEX
    Explanations

    The

    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
    -Semit
    -0.28
    byss
    -0.22
    è¿ĶåĽŀæIJľçĭIJ
    -0.20
    avanaugh
    -0.20
    åĭł
    -0.19
    ltre
    -0.19
    iêu
    -0.19
    ANGLES
    -0.19
    isbury
    -0.19
    ///č↵
    -0.19
    POSITIVE LOGITS
     licensors
    0.23
    æĸ°æµªè´¢ç»ı
    0.22
    intégr
    0.19
    ocrisy
    0.19
    orical
    0.19
    abyrinth
    0.19
    peater
    0.19
    æ»ĺ
    0.19
    çѵ
    0.18
    ÐŁÐ¾Ð´ÑĢобнее
    0.18
    Activations Density 1.918%

    No Known Activations