© 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. 17309
    Prev
    Next
    INDEX
    Explanations

    video compression encoding decoding

    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
     Leather
    -0.20
     hemat
    -0.19
     Cord
    -0.19
    ped
    -0.19
     cord
    -0.19
     plat
    -0.19
     Batter
    -0.19
    èľĤ
    -0.19
    hus
    -0.18
    anten
    -0.18
    POSITIVE LOGITS
    åĩºèī²çļĦ
    0.23
    æĬĢæľ¯åĴĮ
    0.21
    \xb
    0.21
    ç¼ĸçłģ
    0.20
    åİĤæĪ¿
    0.20
    åºIJ
    0.20
     subrange
    0.20
    æł¸å¿ĥ
    0.19
    æł¸å¿ĥæĬĢæľ¯
    0.19
    å½ķåĥı
    0.19
    Activations Density 0.014%

    No Known Activations