© 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. 64054
    Prev
    Next
    INDEX
    Explanations

    July dates

    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
    åħĥæŦ
    -0.16
    æĺ¥èĬĤæľŁéĹ´
    -0.16
    å¯ĴåĨ¬
    -0.15
    æĺ¥è¿IJ
    -0.14
    æĺ¥èĬĤ
    -0.14
    éĻ¤å¤ķ
    -0.13
    æĸ°æĺ¥
    -0.12
    -Jan
    -0.12
     зим
    -0.12
    åĨ¬åŃ£
    -0.12
    POSITIVE LOGITS
    ä¸ĥæľĪ
    0.18
    æļijæľŁ
    0.18
     July
    0.17
    å¤ıåŃ£
    0.17
    å¤ıæĹ¥
    0.17
    July
    0.16
    å¤ı天
    0.16
    æļijåģĩ
    0.16
     Jul
    0.15
    å¤ı
    0.15
    Activations Density 0.313%

    No Known Activations