© 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. 10472
    Prev
    Next
    INDEX
    Explanations

    knowledgeable experts or specialized staff

    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
    èļĬ
    -0.21
    è°ľ
    -0.19
    çļĦè®°å¿Ĩ
    -0.19
    ä¸įå¼Ģ
    -0.19
    .sponge
    -0.18
    漪
    -0.18
    éģı
    -0.18
    æŁ³
    -0.18
    宾
    -0.18
    大人
    -0.18
    POSITIVE LOGITS
     expertise
    0.37
    ç²¾éĢļ
    0.33
     knowledgeable
    0.31
    æĩĤ
    0.29
     specialized
    0.27
    ä¸ĵ家
    0.27
    ä¸ĵä¸ļçŁ¥è¯Ĩ
    0.27
    expert
    0.27
     Expert
    0.26
    è°Ļ
    0.25
    Activations Density 0.136%

    No Known Activations