© 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. 10575
    Prev
    Next
    INDEX
    Explanations

    version numbers and .tar files

    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
    -centric
    -0.18
    arella
    -0.18
    oose
    -0.18
    æľªæĿ¥çļĦ
    -0.17
    chie
    -0.17
    theses
    -0.17
    ç£Ķ
    -0.17
    vig
    -0.17
    两家
    -0.16
    ivant
    -0.16
    POSITIVE LOGITS
    çīĪæľ¬
    0.21
    以æĿ¥
    0.20
    æļ¨
    0.20
     version
    0.19
    âĢ³
    0.19
    è¿Ń代
    0.19
    -banner
    0.18
    çīĪ
    0.18
     iteration
    0.17
     onwards
    0.17
    Activations Density 0.115%

    No Known Activations