© 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. 17285
    Prev
    Next
    INDEX
    Explanations

    files (the "Software")

    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
    çĶŁç´ł
    -0.21
    äºĮ线
    -0.20
    èĥ½ä½¿
    -0.19
    ÑĤем
    -0.18
    ä¸Ģ线
    -0.18
    ãĥ£
    -0.18
    幡
    -0.18
    åĪº
    -0.17
     suspense
    -0.17
    åIJİ代
    -0.17
    POSITIVE LOGITS
    patial
    0.21
    çķĻä¸ĭæĿ¥
    0.18
    IRTH
    0.18
    nces
    0.18
    æĻ®éĢļè¯Ŀ
    0.18
    endencies
    0.18
    è¡Į为
    0.17
    ingu
    0.17
     seo
    0.17
    ACCEPT
    0.17
    Activations Density 0.008%

    No Known Activations