© 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. 60793
    Prev
    Next
    INDEX
    Explanations

    warnings, part, update, copyright, ball, pool

    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
    åģĪ
    -0.09
    æľ¬è½®
    -0.09
    éļıå¤Ħ
    -0.08
    头顶
    -0.08
    åħ¨è¦ĨçĽĸ
    -0.08
    èĸľ
    -0.08
    毫æĹłçĸij
    -0.08
     Hp
    -0.08
    å¿ĥ仪
    -0.08
    eson
    -0.08
    POSITIVE LOGITS
    è¿ŀè½½
    0.09
    obia
    0.09
    æĸ°é¢ĸ
    0.09
    æĶ¶æĶ¯
    0.08
    ä½ľåĵģ
    0.08
    amus
    0.08
    æ¯ĶèµĽ
    0.08
    릴
    0.08
    人æ°Ķ
    0.08
     SND
    0.08
    Activations Density 0.012%

    No Known Activations