© 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. Qwen3-14B
    5. 20-RESID-BATCHTOPK-65K__L0-80
    7. 17151
    Prev
    Next
    INDEX
    Explanations

    ordinary or traditional

    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
    Negative Logits
    å¹½é»ĺ
    -0.22
     dÆ°Æ¡ng
    -0.21
    èĭ¦
    -0.20
    åľ¨çĶŁæ´»ä¸Ń
    -0.20
    åIJĦ个æĸ¹éĿ¢
    -0.19
    åĴĮå°ļ
    -0.19
    çĽ¼æľĽ
    -0.19
    izzard
    -0.18
    Altern
    -0.18
    å¿įä¸įä½ı
    -0.18
    POSITIVE LOGITS
    æĻ®éĢļçļĦ
    0.30
    ä¸ĢèĪ¬çļĦ
    0.27
    ä¼łç»ŁçļĦ
    0.26
    åįķ纯çļĦ
    0.24
    æĻ®éĢļ
    0.23
    éĤ£ç§į
    0.23
    èĢĮæĺ¯
    0.23
     ordinary
    0.21
     traditional
    0.21
    åĪ»
    0.21
    Activations Density 0.033%

    No Known Activations