© 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. Qwen3-14B
    5. 20-RESID-BATCHTOPK-65K__L0-80
    7. 11029
    Prev
    Next
    INDEX
    Explanations

    namely

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    adamkarvonen/qwen3-14b-saes/saes_Qwen_Qwen3-14B_batch_top_k/resid_post_layer_20
    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
    注æĦıåĪ°
    -0.23
    æıł
    -0.20
    æľī趣
    -0.20
    FAULT
    -0.19
    è¿Ļæĺ¯
    -0.19
    åľ¨è¿Ļæĸ¹éĿ¢
    -0.19
    ivors
    -0.19
    注æĦı
    -0.18
    ä¸įè´Ł
    -0.18
     ÐŀÑģоб
    -0.18
    POSITIVE LOGITS
    éĤ£å°±æĺ¯
    0.45
     namely
    0.33
     ë°Ķë¡ľ
    0.26
    ä»Ģä¹Īåij¢
    0.26
    nam
    0.25
    çļĦå°±æĺ¯
    0.25
     nämlich
    0.25
    èİ«è¿ĩäºİ
    0.22
    å°±æĺ¯
    0.21
    便æĺ¯
    0.20
    Activations Density 0.108%

    No Known Activations