© 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. 2366
    Prev
    Next
    INDEX
    Explanations

    model

    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
    /Dk
    -0.35
    rarian
    -0.29
    ;');↵
    -0.28
    imeline
    -0.28
    ');↵↵↵↵
    -0.28
    ;};↵
    -0.27
     "></
    -0.27
    ",__
    -0.27
    alyzed
    -0.27
    ")));
    -0.26
    POSITIVE LOGITS
    ãĢĤwww
    0.29
    æĢ§ä»·
    0.28
    对çħ§æ£ĢæŁ¥
    0.28
    纰
    0.27
    åıĸåĨ³
    0.27
     desar
    0.27
    ä¸įèī¯ä¿¡æģ¯
    0.27
    èµħ
    0.26
    led
    0.26
     maç
    0.26
    Activations Density 0.123%

    No Known Activations