© 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. 1227
    Prev
    Next
    INDEX
    Explanations

    sentence end

    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
    :";č↵
    -0.32
    Then
    -0.28
     enthusi
    -0.26
     Lastly
    -0.26
    è¿ĺæľīä¸ĢäºĽ
    -0.25
     Meanwhile
    -0.24
    åı¦æľī
    -0.24
     THEN
    -0.23
     then
    -0.23
    çĦ¶åIJİ
    -0.23
    POSITIVE LOGITS
    é¦ĸåħĪ
    0.50
    é¦ĸåħĪæĺ¯
    0.47
    ä¸Ģæĸ¹éĿ¢
    0.36
    æ¯ķç«Ł
    0.35
     ÐĴедÑĮ
    0.35
    ä¸Ģæĺ¯
    0.35
     Firstly
    0.34
    åħĪæĺ¯
    0.34
     nämlich
    0.33
    é¦ĸåħĪè¦ģ
    0.33
    Activations Density 3.621%

    No Known Activations