© 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. 60597
    Prev
    Next
    INDEX
    Explanations

    enhance the experience

    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
     Äijủ
    -0.11
    à§İ
    -0.10
    æ¯ķ
    -0.10
    ä¼ļéķ¿
    -0.09
    å¯Ĩçłģ
    -0.09
    å¯Ĩ碼
    -0.09
    å¾Īé«ĺåħ´
    -0.09
    åħ¨éķ¿
    -0.08
    orges
    -0.08
    çķ¢
    -0.08
    POSITIVE LOGITS
    å¢ŀæ·»
    0.13
    å¢ŀæ·»äºĨ
    0.12
    æĽ´åħ·
    0.11
    ä¹ĭåĬ¿
    0.10
     enrich
    0.10
    æĽ´æľī
    0.09
    éĻĦåĬłåĢ¼
    0.09
    å¢ŀåĬł
    0.09
    åİŁæľī
    0.09
    档次
    0.09
    Activations Density 0.085%

    No Known Activations