© 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. 1157
    Prev
    Next
    INDEX
    Explanations

    of

    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
    à¹Ģà¸Ĥา
    -0.27
    éĩįçĤ¹
    -0.27
    ÙĤدÙĬر
    -0.24
    ä¼ģä¸ļ
    -0.22
     licensors
    -0.22
    orious
    -0.22
     of
    -0.22
    à¹Ģรา
    -0.21
     acompaña
    -0.21
     "{"
    -0.21
    POSITIVE LOGITS
     sorts
    0.49
    esteem
    0.35
    à¥IJ
    0.32
    .dtd
    0.31
    /↵↵↵↵
    0.30
    pisa
    0.30
    .MouseAdapter
    0.29
    /,↵
    0.28
    æĢ»èĢĮè¨Ģ
    0.28
    course
    0.28
    Activations Density 3.245%

    No Known Activations