© 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. 17108
    Prev
    Next
    INDEX
    Explanations

    capstan, volumes, East, attempts, Airbrush, lifeguard

    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
    borg
    -0.20
    lsi
    -0.20
    ç¾ļ
    -0.19
    jong
    -0.18
    Ana
    -0.17
     caret
    -0.17
    é³ŀ
    -0.17
    hood
    -0.17
    loth
    -0.17
    çľĭçĿĢ
    -0.17
    POSITIVE LOGITS
    çļĦ女人
    0.18
    女æĸ¹
    0.17
    夫人
    0.17
    ressive
    0.17
     Roose
    0.17
    鱼类
    0.17
     Erick
    0.17
    obi
    0.17
    /MIT
    0.17
     designate
    0.16
    Activations Density 0.844%

    No Known Activations