© 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. 47485
    Prev
    Next
    INDEX
    Explanations

    organization, executives, secretary, leader

    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
    çļĩå¸Ŀ
    -0.09
     HoÃłng
    -0.09
    èIJ¥åķĨçݯå¢ĥ
    -0.09
     bounty
    -0.09
     Emperor
    -0.09
    çļĩä¸Ĭ
    -0.08
    滢
    -0.08
    èĪľ
    -0.08
     Flash
    -0.08
    Flash
    -0.08
    POSITIVE LOGITS
    ä¼ļåijĺ
    0.13
    åĪĨæĶ¯æľºæŀĦ
    0.13
    æĪIJåijĺ
    0.12
    æľĥåĵ¡
    0.12
     membership
    0.12
     member
    0.11
    æĢ»éĥ¨
    0.11
    membership
    0.10
    åħ±éĿĴåĽ¢
    0.10
     Membership
    0.10
    Activations Density 0.226%

    No Known Activations