© 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. 47447
    Prev
    Next
    INDEX
    Explanations

    ordinary people

    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
    æĭį
    -0.10
    æĹłå½¢
    -0.10
    ä¸įéĻIJ
    -0.10
    æĺİæĺ¾çļĦ
    -0.09
    åĽº
    -0.09
    oyer
    -0.09
     Chall
    -0.09
    å®īæħ°
    -0.08
    åIJĦåľ°
    -0.08
    åIJĦæĸ¹
    -0.08
    POSITIVE LOGITS
    æĻ®éĢļ人
    0.23
    èĢģçĻ¾å§ĵ
    0.22
    æĻ®éĢļ
    0.22
    çĻ¾å§ĵ
    0.21
    å¹³æ°ij
    0.18
     ordinary
    0.17
    æĻ®éĢļçļĦ
    0.16
    ordinary
    0.16
    æ°ijä¼Ĺ
    0.15
    寻常
    0.15
    Activations Density 0.079%

    No Known Activations