© 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. 59461
    Prev
    Next
    INDEX
    Explanations

    gerunds indicating action or process

    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
    ÂŃing
    -0.09
    лÑİ
    -0.09
    åľ°æĸ¹
    -0.09
    彩
    -0.09
    lectric
    -0.09
    æijĩ头
    -0.08
    ABLE
    -0.08
    onte
    -0.08
    éŨåīį
    -0.08
    åĪĹ为
    -0.08
    POSITIVE LOGITS
    ç®ĹäºĨ
    0.09
    ä¸Ĭæľī
    0.08
    éĴĬ
    0.08
    éĻ´
    0.08
    ä¸ĢåĽ¢
    0.08
    ensis
    0.08
    ìľ¼ë©°
    0.08
    çĦ¼
    0.08
    ä¸ŃåIJ«æľī
    0.08
    åĽ¢
    0.08
    Activations Density 0.239%

    No Known Activations