© 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. 17316
    Prev
    Next
    INDEX
    Explanations

    about the day

    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
    æ¯ıå¹´
    -0.24
    ç«¥
    -0.23
    ç»Ī身
    -0.22
     bó
    -0.21
    没éĶĻ
    -0.21
    éĢIJå¹´
    -0.21
    aina
    -0.21
    åįģå¹´
    -0.21
    ä¼ĹæīĢåij¨çŁ¥
    -0.21
     forever
    -0.20
    POSITIVE LOGITS
    æľ¬åij¨
    0.24
    æĺ¨æĻļ
    0.23
    Yesterday
    0.23
     yesterday
    0.23
    æĺ¨å¤©
    0.23
    ä¹ħãģĹãģ¶ãĤĬ
    0.22
     ÑħозÑıйÑģÑĤв
    0.21
    æķĻçłĶ
    0.21
    ä¸Ĭåij¨
    0.20
    è¿Ļ两天
    0.20
    Activations Density 0.129%

    No Known Activations