© 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. 17159
    Prev
    Next
    INDEX
    Explanations

    Drosophila

    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
    izzo
    -0.25
    å¼ĢåĬŀ
    -0.22
    åIJĦçľģ
    -0.21
     Trom
    -0.21
    åIJ¬åıĸ
    -0.20
    æ»Ķ
    -0.20
    ayah
    -0.19
    pty
    -0.19
    éĽĦåİļ
    -0.19
     Victorian
    -0.18
    POSITIVE LOGITS
    æľīåIJįçļĦ
    0.23
    пÑĥÑī
    0.19
     Armen
    0.18
     Stard
    0.18
     heter
    0.18
    åįĬå¤ľ
    0.18
     ìĥĿëªħ
    0.18
     uncovered
    0.18
    PLUS
    0.18
    à¹Ģศรษà¸IJ
    0.18
    Activations Density 0.107%

    No Known Activations