© 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. 10658
    Prev
    Next
    INDEX
    Explanations

    still exists or continues

    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
    çİ°åľ¨å·²ç»ı
    -0.23
    åīį段æŶéĹ´
    -0.21
    éĤ£ä½ł
    -0.21
    ä¸ĢçĽ´ä»¥æĿ¥
    -0.20
    ä¸įå®Į
    -0.20
    æĺ¨å¤©
    -0.19
    ä¹Łä¸įæķ¢
    -0.19
    ä»İæĿ¥æ²¡
    -0.19
    éĤ£æ¬¡
    -0.18
    å§ĭç»Ī
    -0.18
    POSITIVE LOGITS
    æĮģæľī
    0.22
    使çĶ¨çļĦ
    0.21
    aina
    0.20
    ãģķãĤī
    0.20
    æĮģæľīçļĦ
    0.19
    аÑĢа
    0.19
    Captain
    0.19
    s
    0.19
    éļ½
    0.19
    ExceptionHandler
    0.18
    Activations Density 0.042%

    No Known Activations