© 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. 16754
    Prev
    Next
    INDEX
    Explanations

    International before a noun

    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
    æ²ī
    -0.20
    eyJ
    -0.20
    oy
    -0.19
    uff
    -0.18
    ic
    -0.18
    å¿Ŀ
    -0.18
    ster
    -0.18
     tar
    -0.17
     bil
    -0.17
    -based
    -0.17
    POSITIVE LOGITS
    æł·çļĦ
    0.22
    åķĨæĬ¥
    0.20
    หมà¸Ķ
    0.19
     Roma
    0.18
    ฯ
    0.18
    西æ´ĭ
    0.18
    éĽªèĬ±
    0.17
    éĻªä½ł
    0.17
    åIJĦåĽ½
    0.17
     vÃŃde
    0.17
    Activations Density 0.032%

    No Known Activations