© 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. 29388
    Prev
    Next
    INDEX
    Explanations

    fishing, Kingfisher, Ford, calves, Schweitzer

    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
    忽çķ¥äºĨ
    -0.09
    磫
    -0.09
    åĽ½æĹĹ
    -0.09
    flags
    -0.08
    æĹĮ
    -0.08
    饼干
    -0.08
    åĪĨå±Ģ
    -0.08
    ãģĮãĤī
    -0.08
    åİŁæľī
    -0.08
    è·Łä¸įä¸Ĭ
    -0.08
    POSITIVE LOGITS
    æĪijçļĦå¿ĥ
    0.10
    è°£
    0.09
    æĪijå¿ĥéĩĮ
    0.09
    æĪĴ
    0.09
    骡
    0.09
     ÅĽwiad
    0.09
    åĹĴ
    0.09
    解æĶ¾æĢĿæĥ³
    0.08
    æĪĺçķ¥å¸ĥå±Ģ
    0.08
    æ´½
    0.08
    Activations Density 0.002%

    No Known Activations