© 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-65K
    7. 4105
    Prev
    Next
    INDEX
    Explanations

    contradiction

    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
    Negative Logits
    "default
    -0.23
    icions
    -0.23
    oenix
    -0.21
    stice
    -0.21
    åıªçŁ¥éģĵ
    -0.19
    [arg
    -0.19
    ".↵↵↵↵
    -0.18
    ä¸īåĨľ
    -0.18
    åĸľ
    -0.18
    intendo
    -0.18
    POSITIVE LOGITS
    æĺ¯ä¸įåı¯èĥ½
    0.43
     contrad
    0.35
    ä¸į符åIJĪ
    0.33
    è¿ĿèĥĮ
    0.33
     contradiction
    0.33
    ä¸įåı¯èĥ½
    0.32
    unlikely
    0.31
    æĢİä¹Īåı¯èĥ½
    0.30
    Contr
    0.29
    æĺ¾çĦ¶æĺ¯
    0.28
    Activations Density 0.222%

    No Known Activations