© 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. 6164
    Prev
    Next
    INDEX
    Explanations

    Bates, James

    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
    ä¸ĢéĿ¢
    -0.09
    鲧
    -0.09
    æįŀ
    -0.09
    ier
    -0.09
    çĨ¹
    -0.08
    å·¥ä½ľæĬ¥åijĬ
    -0.08
    ered
    -0.08
    åłĩ
    -0.08
    èµĪ
    -0.08
    8
    -0.08
    POSITIVE LOGITS
    ÑģÑı
    0.11
    доб
    0.09
    é¦Ĺ
    0.09
    æİĮ
    0.09
    EUR
    0.09
    åŃ
    0.09
     ÑĢол
    0.09
    ãĤĤãģĨ
    0.09
    Fully
    0.08
    ted
    0.08
    Activations Density 0.017%

    No Known Activations