© 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. 10519
    Prev
    Next
    INDEX
    Explanations

    saint, knight, Honor

    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
    åľĨ满å®ĮæĪIJ
    -0.23
    幸ç¦ıæĦŁ
    -0.19
    AppState
    -0.19
    éķĸ
    -0.19
    æĮīæŶ
    -0.19
    çŁ¥éģĵèĩªå·±
    -0.19
    ÑĩÑĮ
    -0.19
    è·Łè¸ª
    -0.18
    裸
    -0.18
     жÑĥÑĢнал
    -0.18
    POSITIVE LOGITS
    æī¹åĩĨ
    0.23
     officially
    0.22
    erti
    0.22
    çļĦ人çī©
    0.21
    èµ·æĿ¥
    0.20
     Approved
    0.20
    举
    0.20
    ously
    0.20
    èµ·æĿ¥äºĨ
    0.20
    hood
    0.20
    Activations Density 0.006%

    No Known Activations