© 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. 1115
    Prev
    Next
    INDEX
    Explanations

    their

    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
    å®ĥçļĦ
    -0.30
     itself
    -0.29
    Its
    -0.29
     коÑĤоÑĢое
    -0.28
    æĺ¯ä¸Ģä½į
    -0.28
     Its
    -0.27
    æĺ¯ä¸ĢåIJį
    -0.27
    æĪIJ为ä¸Ģ个
    -0.27
    ãĢĤwww
    -0.26
    æĪIJ为ä¸ĢåIJį
    -0.26
    POSITIVE LOGITS
     themselves
    1.12
    ä»ĸ们çļĦ
    0.91
     their
    0.86
    åIJĦèĩª
    0.83
    their
    0.79
    åIJĦèĩªçļĦ
    0.79
    Their
    0.77
     Their
    0.75
     иÑħ
    0.66
     leurs
    0.64
    Activations Density 7.053%

    No Known Activations