© 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. 17176
    Prev
    Next
    INDEX
    Explanations

    spreadsheet column, application windows

    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
    ellig
    -0.21
    velt
    -0.20
     неÑģк
    -0.18
    ä¹Łæĺ¯éĿŀ常
    -0.18
    aval
    -0.18
     intents
    -0.18
     Morr
    -0.17
    oley
    -0.17
    iry
    -0.17
     bè
    -0.17
    POSITIVE LOGITS
    çļĦ第ä¸Ģ
    0.20
    è°ģçŁ¥éģĵ
    0.20
    çļĦ第ä¸Ģ个
    0.20
    ãģķãģĪ
    0.20
    ä¸Ńæľī
    0.20
    表çݰ为
    0.19
    é¦ĸ家
    0.19
    Baseline
    0.19
    干线
    0.19
    åľ¨åĵª
    0.19
    Activations Density 0.836%

    No Known Activations