© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen2.5-7B-IT
    5. 20-MATRYOSHKA-CHAT-65K
    7. 46779
    Prev
    Next
    INDEX
    Explanations

    large numbers

    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/lmsys/matryoshka/k-100
    Prompts (Dashboard)
    16,384 prompts, 192 tokens each
    Dataset (Dashboard)
    chanind/lmsys-chat-1m-qwen-2.5
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    berapa
    -0.23
    '>".$
    -0.21
    ëĴĢ
    -0.21
    åĩłä¸ª
    -0.20
     yıl
    -0.20
    .setBackgroundResource
    -0.19
     awhile
    -0.19
    three
    -0.19
    	TArray
    -0.19
    åĩłå®¶
    -0.19
    POSITIVE LOGITS
     thousands
    0.40
    累计
    0.39
     hundreds
    0.36
    æį®ç»Łè®¡
    0.34
     tens
    0.32
     Thousands
    0.32
     millions
    0.32
     Hundreds
    0.31
     nearly
    0.31
     billions
    0.30
    Activations Density 0.146%

    No Known Activations