© 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. 16742
    Prev
    Next
    INDEX
    Explanations

    He followed by verb of achievement

    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
    å·²ç»ıåľ¨
    -0.09
    æŀ¢
    -0.09
    isha
    -0.08
    ç®Ķ
    -0.08
    æĿĨ
    -0.08
    æį§
    -0.08
    è¿ijæĹ¥
    -0.08
    çİ°æľīçļĦ
    -0.08
    æĺ¨å¤©
    -0.08
    ä¸įç¡®å®ļ
    -0.08
    POSITIVE LOGITS
    æĻļå¹´
    0.17
    éĢĢä¼ij
    0.15
    ç»Ī身
    0.11
    ç»ĪçĶŁ
    0.11
    æŃ»åIJİ
    0.11
    ä¸ĢçĶŁ
    0.11
    ç»Ī
    0.10
     retiring
    0.10
     Retirement
    0.10
    æĭĦ
    0.09
    Activations Density 0.419%

    No Known Activations