© 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. 10518
    Prev
    Next
    INDEX
    Explanations

    auxiliary verbs

    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
    hower
    -0.19
    verty
    -0.18
    人çĶŁçļĦ
    -0.18
    奥巴
    -0.18
    鬯
    -0.18
    å¾Īæ¼Ĥ亮
    -0.17
    åIJĮæĥħ
    -0.17
    \\/
    -0.17
    çĬ¶æĢģä¸ĭ
    -0.17
    çĶŁæ´»çļĦ
    -0.17
    POSITIVE LOGITS
    راÙħ
    0.20
    çĥ¹
    0.19
    ued
    0.19
    åĺ¿
    0.18
    èĢĮ对äºİ
    0.18
    ä»ĸçļĦ
    0.18
    /is
    0.18
    /math
    0.17
     sus
    0.17
    ä»ĸ认为
    0.17
    Activations Density 0.131%

    No Known Activations