© 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. 10463
    Prev
    Next
    INDEX
    Explanations

    unic prefix

    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
    ening
    -0.19
    weise
    -0.19
    è¡·
    -0.17
    ighth
    -0.17
    ses
    -0.17
    ively
    -0.17
    atoon
    -0.16
    ä¸įåIJĪæł¼
    -0.16
    ough
    -0.16
    abouts
    -0.16
    POSITIVE LOGITS
    ç§ijæĬĢåĽŃ
    0.18
     ÑģвÑıзи
    0.17
    isex
    0.17
    оÑĢ
    0.16
    OfWork
    0.16
    å½±ä¸ļ
    0.15
    åĽ¾æĸĩ
    0.15
    æ¸ħæ¾Ī
    0.15
    衾
    0.15
    fried
    0.15
    Activations Density 0.029%

    No Known Activations