© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen2.5-7B-IT
    5. 20-MATRYOSHKA-65K
    7. 3044
    Prev
    Next
    INDEX
    Explanations

    existence

    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
    çģĮ
    -0.22
    éĥIJ
    -0.20
    é¢ł
    -0.19
    ä¸įå®ľ
    -0.19
    æĮ½
    -0.19
    éģĵ
    -0.19
    ä¸Ģè´¯
    -0.18
     FIXED
    -0.18
     UINavigationController
    -0.18
    ={({
    -0.18
    POSITIVE LOGITS
     existence
    0.47
    åŃĺåľ¨
    0.37
     Exist
    0.36
     exist
    0.35
    åŃĺåľ¨çļĦ
    0.35
    ä¸įåŃĺåľ¨
    0.35
     exists
    0.35
     existe
    0.34
    çļĦåŃĺåľ¨
    0.33
     nonexistent
    0.33
    Activations Density 0.603%

    No Known Activations