© 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. 1060
    Prev
    Next
    INDEX
    Explanations

    age and classification

    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
    âļĹ
    -0.34
    جرÙĬدة
    -0.28
    åľ¨è¿ĩ渡
    -0.27
    ðŁĵIJ
    -0.27
    æľīæĦıæĢĿçļĦ
    -0.25
    StackNavigator
    -0.24
     Após
    -0.24
    ä¸Ģ个èģĮä¸ļ
    -0.23
     neger
    -0.23
     Girlfriend
    -0.23
    POSITIVE LOGITS
    ä¸ĭéĿ¢å°ıç¼ĸ
    0.23
    ä»Ĭ天å°ıç¼ĸ
    0.21
    åIJ©
    0.21
    immutable
    0.20
    ,
    0.20
    commended
    0.20
    ispers
    0.20
     		↵
    0.19
    æĪķ
    0.19
    /npm
    0.18
    Activations Density 6.072%

    No Known Activations