© 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. 847
    Prev
    Next
    INDEX
    Explanations

    text characters

    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
     mktime
    -0.23
    strtotime
    -0.23
     latina
    -0.22
    -nil
    -0.22
    -await
    -0.22
     busty
    -0.21
    (logits
    -0.21
    女æĢ§æľĭåıĭ
    -0.21
    æĺ
    -0.21
    .radians
    -0.21
    POSITIVE LOGITS
    æĸ°æµªè´¢ç»ı
    0.27
    å¾®åķĨ
    0.25
    âĦħ
    0.25
    ä¼łå¥ĩ游æĪı
    0.25
    å¿ĥå¾Ĺä½ĵä¼ļ
    0.24
     characters
    0.23
     @"\
    0.23
    举æĸ¹è´¢å¯Į
    0.23
     word
    0.23
    /*↵
    0.23
    Activations Density 2.947%

    No Known Activations