© 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. 26034
    Prev
    Next
    INDEX
    Explanations

    flat panel display

    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
    edin
    -0.10
    çļĦæĸĩåŃĹ
    -0.10
     ìĸ¸
    -0.10
    趣
    -0.09
    éļ§
    -0.09
    åŁĭ
    -0.09
    误åĮº
    -0.09
     Rosenstein
    -0.09
    ä¸Ģ件
    -0.09
    éĽ
    -0.09
    POSITIVE LOGITS
    AMED
    0.09
    ssel
    0.08
    éĢļé£İ
    0.08
    å¢Ļä¸Ĭ
    0.08
     dominance
    0.08
     HD
    0.08
    ãģĹãĤĩãģĨ
    0.08
    .utcnow
    0.08
    çĶµè§Ĩ
    0.08
    uro
    0.08
    Activations Density 0.280%

    No Known Activations