© 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. 26287
    Prev
    Next
    INDEX
    Explanations

    breaking news or stories

    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
    è¯ŀ
    -0.11
     Tra
    -0.09
    Tra
    -0.09
    èĮĥ
    -0.09
    uble
    -0.09
    æŀª
    -0.09
    èĩªæ²»
    -0.09
    æŃ¥åħ¥
    -0.08
    没äºĭ
    -0.08
    æŀ£
    -0.08
    POSITIVE LOGITS
    æĬ¥éģĵ
    0.15
     news
    0.12
    æĸ°éĹ»ä¸Ńå¿ĥ
    0.12
     News
    0.11
    æĸ°éĹ»
    0.11
    æĬ¥éģĵ称
    0.11
    åł±å°İ
    0.11
    ãĥĭãĥ¥ãĥ¼ãĤ¹
    0.10
    快讯
    0.10
    件äºĭ
    0.10
    Activations Density 0.140%

    No Known Activations