© 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. 46869
    Prev
    Next
    INDEX
    Explanations

    data fields

    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
    Negative Logits
    -await
    -0.22
    #End
    -0.20
     AsyncStorage
    -0.19
     MouseButton
    -0.19
    çĮ·
    -0.18
     máximo
    -0.18
    named
    -0.18
     Fist
    -0.18
     SqlParameter
    -0.18
    iales
    -0.18
    POSITIVE LOGITS
    :bold
    0.23
    ï¼ģ');↵
    0.22
    纰
    0.22
    otron
    0.21
    æĿ¥çľĭçľĭåIJ§
    0.21
    .googlecode
    0.21
    è¥ŀ
    0.20
    VERTISE
    0.20
    åĺ§
    0.20
    :UITableView
    0.20
    Activations Density 0.001%

    No Known Activations