© 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. 3760
    Prev
    Next
    INDEX
    Explanations

    code and foreign words

    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
    iox
    -0.27
    ıyoruz
    -0.23
    çĦĬæİ¥
    -0.21
    )$/
    -0.21
    prene
    -0.20
    ä¸įå¤ļ
    -0.19
    eparator
    -0.19
    ennen
    -0.19
    ugins
    -0.18
    ymi
    -0.18
    POSITIVE LOGITS
    QDebug
    0.23
    说å®ŀ
    0.22
     madrid
    0.20
    )init
    0.20
    -License
    0.20
    )did
    0.20
    æĸ°æµªè´¢ç»ı
    0.19
     diseñador
    0.19
     caliente
    0.19
    .HandlerFunc
    0.19
    Activations Density 0.001%

    No Known Activations