© 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. 1218
    Prev
    Next
    INDEX
    Explanations

    start or beginning

    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
    []{↵
    -0.26
    ulumi
    -0.26
    :animated
    -0.25
    ä¸ĭéĿ¢æĺ¯å°ı
    -0.23
    )size
    -0.23
    esteem
    -0.22
    "x
    -0.22
    lobals
    -0.22
    вÑĪей
    -0.22
    >tag
    -0.21
    POSITIVE LOGITS
    ä¹ĭåĪĿ
    0.33
    ë¶ĢíĦ°
    0.30
    -start
    0.30
     ìĭľìŀij
    0.30
    =start
    0.29
    /start
    0.29
     beginnings
    0.28
     outset
    0.27
     start
    0.26
    (start
    0.25
    Activations Density 2.839%

    No Known Activations