© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-14B
    5. 20-RESID-BATCHTOPK-65K__L0-80
    7. 13853
    Prev
    Next
    INDEX
    Explanations

    medical conditions and biology

    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
    Not in Any Lists

    No Comments

    Negative Logits
     Honest
    -0.16
    ä¸¥æł¼çļĦ
    -0.15
    å¡«è¡¥
    -0.15
    IOUS
    -0.15
    OLER
    -0.14
     Runs
    -0.14
     Bulk
    -0.14
    è¯¾æľ¬
    -0.14
    Bulk
    -0.14
    æĹłæĦı
    -0.14
    POSITIVE LOGITS
    çŃł
    0.16
    /title
    0.15
    elloworld
    0.15
    å©¢
    0.15
    -blog
    0.14
    ApplicationBuilder
    0.14
    åĻ«
    0.14
    åľ¨è¿Ļæĸ¹éĿ¢
    0.14
    èķĪ
    0.14
    عÙĨÙĬ
    0.14
    Activations Density 11.888%

    No Known Activations