© 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. 60643
    Prev
    Next
    INDEX
    Explanations

    personal pronouns

    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
    éĥ
    -0.11
    éªĸ
    -0.10
    uml
    -0.10
    å¥
    -0.09
    帷
    -0.09
    åºĨ幸
    -0.09
    äºĨèĩªå·±çļĦ
    -0.08
    äºİæѤ
    -0.08
    æĺİæĻº
    -0.08
     itself
    -0.08
    POSITIVE LOGITS
    å½Ģ
    0.09
    æĤ£
    0.09
    oeff
    0.09
    åıĬåħ¶
    0.08
    æĪĸèĢħåħ¶ä»ĸ
    0.08
    zilla
    0.08
    éĢļä¿Ĺ
    0.08
    erra
    0.08
    Jess
    0.08
     behalf
    0.08
    Activations Density 0.060%

    No Known Activations