© 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. 17100
    Prev
    Next
    INDEX
    Explanations

    apps and services

    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
     material
    -0.23
    ener
    -0.21
    æĿIJ
    -0.21
    onde
    -0.21
    æĿŀ
    -0.21
    seo
    -0.20
    SEO
    -0.20
    abajo
    -0.20
     gro
    -0.20
    alers
    -0.19
    POSITIVE LOGITS
     поÑģколÑĮ
    0.25
     erotisk
    0.23
     tjejer
    0.23
    çĻ»éĻĨ
    0.23
     danmark
    0.21
    åĽ¾æłĩ
    0.21
    移æ¤į
    0.21
     bezpo
    0.20
    ä¿¡æģ¯æľįåĬ¡
    0.20
    æ°ijæ£Ģå¯ŁéĻ¢
    0.20
    Activations Density 0.073%

    No Known Activations