© 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. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 26168
    Prev
    Next
    INDEX
    Explanations

    .com domains and media channels

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    adamkarvonen/qwen3-32b-saes/saes_Qwen_Qwen3-32B_batch_top_k/resid_post_layer_32
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    .lineTo
    -0.09
    ãģ»ãģĨ
    -0.08
    å·²æĺ¯
    -0.08
    该éĻ¢
    -0.08
     Zw
    -0.08
    å¥Ĺ
    -0.08
    è¯¥æł¡
    -0.08
    åĬ¨åijĺ
    -0.08
    ãĤģãĤĭ
    -0.08
    çģĮ
    -0.08
    POSITIVE LOGITS
    éĵ¿
    0.09
    RIES
    0.09
    ersion
    0.09
    对åŃ©åŃIJ
    0.09
    UIS
    0.09
    å©ī
    0.09
    æĮĪ
    0.08
    èħ´
    0.08
    ä½
    0.08
    èµ°åĬ¿
    0.08
    Activations Density 0.027%

    No Known Activations