© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-8B
    5. 18-RESID-BATCHTOPK-65K__L0-80
    7. 77
    Prev
    Next
    INDEX
    Explanations

    questions about location

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    adamkarvonen/qwen3-8b-saes/saes_Qwen_Qwen3-8B_batch_top_k/resid_post_layer_18
    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
    å¾Ī满æĦı
    -0.28
    æĺ¯å¾Ī
    -0.27
    éĿŀ常çļĦ
    -0.26
    å¾Īå¼Ģå¿ĥ
    -0.25
    æĺ¯æ²¡æľī
    -0.25
    æĺ¯ä¸Ģ件
    -0.24
    éĿŀ常好çļĦ
    -0.24
    æĺ¯ä¸įä¼ļ
    -0.24
    å¾Ĺå¾Ī好
    -0.23
    è¶³å¤ŁçļĦ
    -0.23
    POSITIVE LOGITS
     seemingly
    0.30
    æĢ»æĺ¯
    0.28
     often
    0.27
     constantly
    0.27
    éĿ¢å¯¹
    0.27
    Facing
    0.26
     now
    0.26
    now
    0.26
    æĬĬ
    0.26
     suddenly
    0.26
    Activations Density 0.222%

    No Known Activations