© 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. 17059
    Prev
    Next
    INDEX
    Explanations

    time, slowness, or duration

    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
    å¾Ī强
    -0.23
    大å°ı
    -0.22
    è¿ħéĢŁ
    -0.22
    åĬłå¿«
    -0.20
     ÑģкоÑĢ
    -0.20
    åħ³å¿ĥ
    -0.19
    å¿«éĢŁ
    -0.19
     سرÙĬع
    -0.19
    æĢ¥éĢŁ
    -0.19
    è¸Ĭ
    -0.19
    POSITIVE LOGITS
    æħ¢
    0.42
     slow
    0.36
     Slow
    0.35
    Slow
    0.35
    ç¼ĵæħ¢
    0.34
    漫éķ¿
    0.33
    slow
    0.33
    å¾Īéķ¿
    0.31
    漫éķ¿çļĦ
    0.31
    èĢĹ
    0.28
    Activations Density 0.192%

    No Known Activations