© 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. 753
    Prev
    Next
    INDEX
    Explanations

    email attachments and signatures

    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
    éĶ¯
    -0.09
    è¯Ĥ
    -0.09
    辫
    -0.09
    以为
    -0.09
    马åĬĽ
    -0.09
    omba
    -0.08
    .githubusercontent
    -0.08
    ä¸Ģ天
    -0.08
    ogue
    -0.08
    审
    -0.08
    POSITIVE LOGITS
    æķ¢
    0.10
    çŁ¿çī©
    0.09
     reconstructed
    0.09
    .sig
    0.09
    å¾ĩ
    0.09
    è¾ĥé«ĺçļĦ
    0.08
    æĺİæĺ¾çļĦ
    0.08
    çıįçıł
    0.08
     gifs
    0.08
    å±ķå¼Ģ
    0.08
    Activations Density 0.131%

    No Known Activations