© 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. 17187
    Prev
    Next
    INDEX
    Explanations

    contesting, following races

    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
    æ¯ı次
    -0.20
    ÙħÙĨاسب
    -0.20
    /pg
    -0.19
     Rex
    -0.19
    ç¦ģåĮº
    -0.19
     Zuk
    -0.18
    ÑĢаниÑĨ
    -0.18
    æŃ£éĿ¢
    -0.18
    çĽ¸äº²
    -0.18
    rint
    -0.17
    POSITIVE LOGITS
    第ä¸ĢåIJį
    0.27
    个ä½ĵ
    0.24
     individual
    0.24
    个åĪ«
    0.24
     individually
    0.23
    Individual
    0.23
    Independent
    0.23
     Individual
    0.23
    æĪIJ绩
    0.23
    çĭ¬ç«ĭ
    0.22
    Activations Density 0.075%

    No Known Activations