© 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. 16719
    Prev
    Next
    INDEX
    Explanations

    president of the United States

    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
    人家
    -0.09
    éļ¾æĢª
    -0.09
    æĬµ
    -0.09
    tro
    -0.09
    磩
    -0.08
    æľĪåºķ
    -0.08
     Liber
    -0.08
    ilit
    -0.08
    å§ľ
    -0.08
    è·¨çķĮ
    -0.08
    POSITIVE LOGITS
    Draft
    0.10
    éĢIJ
    0.09
    /problems
    0.09
    èµĪ
    0.09
    强æľīåĬĽ
    0.09
    ãĥĢãĥ³
    0.08
    ilyn
    0.08
    åĮį
    0.08
    icl
    0.08
     draft
    0.08
    Activations Density 0.104%

    No Known Activations