© 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. 40297
    Prev
    Next
    INDEX
    Explanations

    entertainment and gaming

    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
    éħįä¸Ĭ
    -0.12
    åĽºå®ļçļĦ
    -0.11
    æ²¥
    -0.10
    æŀ¯
    -0.10
    çħŀ
    -0.09
    çIJĨæĻº
    -0.09
    æĶ¶æ¬¾
    -0.09
    æ´¹
    -0.09
    åĬŁè¯¾
    -0.09
    éĥ½æĺ¯éĿŀ常
    -0.09
    POSITIVE LOGITS
    娱ä¹IJ
    0.17
    ä¼ijéĹ²
    0.14
    å¨Ľæ¨Ĥ
    0.14
     entertainment
    0.12
    å¼Ģçİ©ç¬ij
    0.12
    åį¡éĢļ
    0.11
     recreational
    0.11
    çݩ游æĪı
    0.11
     gaming
    0.10
    çİ©èĢį
    0.10
    Activations Density 0.302%

    No Known Activations