© 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. 24212
    Prev
    Next
    INDEX
    Explanations

    gun control and marriage laws

    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
    çķ«
    -0.10
    主èIJ¥ä¸ļåĬ¡
    -0.09
    æ½
    -0.09
    éĹº
    -0.09
    åħħ滿
    -0.09
    hcp
    -0.09
    æĺ¯ä¸įä¼ļ
    -0.09
    éĿŀ常å¤ļçļĦ
    -0.08
    åħħ满
    -0.08
    олж
    -0.08
    POSITIVE LOGITS
     Leone
    0.09
    æݪ
    0.09
    æݪæĸ½
    0.09
    Enlarge
    0.08
    æĺİæĹ¥
    0.08
     medidas
    0.08
    å®ŀäºĭæ±Ĥ
    0.08
    èĢ³è¾¹
    0.07
    åij¨äºĶ
    0.07
    æĶ¿çŃĸ
    0.07
    Activations Density 0.012%

    No Known Activations