© 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. 26036
    Prev
    Next
    INDEX
    Explanations

    anarchist or marxist activists

    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
    æīĵ交éģĵ
    -0.10
     Bowl
    -0.09
    åįļæĸĩ
    -0.09
    ä¼Ĺ
    -0.08
    èĻŀ
    -0.08
     Recap
    -0.08
    iron
    -0.08
    TRL
    -0.08
    .wh
    -0.08
     exter
    -0.08
    POSITIVE LOGITS
    æĶ¯æı´
    0.11
    äºĶä¸Ģ
    0.10
    èijĽ
    0.10
    storeId
    0.09
    ä¸Ģåı£
    0.09
    çĭ±
    0.09
    æĪij们认为
    0.09
    æĴķ
    0.09
    è±¹
    0.09
    åijĽ
    0.09
    Activations Density 0.197%

    No Known Activations