© 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. 10531
    Prev
    Next
    INDEX
    Explanations

    theater and drama

    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
    èĻij
    -0.21
    æĥļ
    -0.20
    Slinky
    -0.20
    åŁºåĩĨ
    -0.19
    åĿĩè¡¡
    -0.19
    _ble
    -0.18
    çIJĨæĢ§
    -0.18
    æħ®
    -0.18
    轸
    -0.18
    weets
    -0.17
    POSITIVE LOGITS
    æ¼Ķåĩº
    0.31
    æĪıåī§
    0.30
    表æ¼Ķ
    0.29
    è¯Ŀåī§
    0.28
     theater
    0.28
    .Actor
    0.27
    åī§éĻ¢
    0.26
    ðŁİŃ
    0.26
     theatre
    0.25
    æ¼Ķ
    0.25
    Activations Density 0.074%

    No Known Activations