© 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. 972
    Prev
    Next
    INDEX
    Explanations

    numbers as 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
    ä¸ĭéĿ¢å°ıç¼ĸ
    -0.24
    traî
    -0.23
    s
    -0.23
    à¸Ħà¸ĵะà¸ģรรมà¸ģาร
    -0.23
    è¿ĶåĽŀæIJľçĭIJ
    -0.23
    .printStackTrace
    -0.22
     rozp
    -0.22
     "><
    -0.20
    ä»Ĭ天å°ıç¼ĸ
    -0.20
     numberWith
    -0.19
    POSITIVE LOGITS
    fold
    0.37
    ieme
    0.32
    -dimensional
    0.30
    -fold
    0.26
    ToOne
    0.25
    ième
    0.25
    rescia
    0.25
    째
    0.25
    ILLISECONDS
    0.25
    -way
    0.25
    Activations Density 1.699%

    No Known Activations