© 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. 13687
    Prev
    Next
    INDEX
    Explanations

    at we

    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
    騰
    -0.20
    沿
    -0.19
    对åºĶçļĦ
    -0.19
    é»İ
    -0.19
    æĮij
    -0.18
    æļ´
    -0.18
    æ§İ
    -0.18
    éĺ¶
    -0.18
    æĽ¾åľ¨
    -0.18
    ëĿ¼ëıĦ
    -0.18
    POSITIVE LOGITS
    ä¸İä¼Ĺä¸įåIJĮ
    0.24
    ä¸įåĥı
    0.22
    åį¯
    0.21
     democr
    0.21
    被çĽĹ
    0.20
     Ñĥме
    0.20
    styleType
    0.20
    ä»Ģä¹Īäºĭ
    0.20
    æݨå´ĩ
    0.20
    ä¸»å¼ł
    0.20
    Activations Density 0.079%

    No Known Activations