© 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. 12297
    Prev
    Next
    INDEX
    Explanations

    women's studies/health/sports

    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
    forth
    -0.09
    ãĥĢãĥ³
    -0.09
    æī¼
    -0.09
    å¢ŀè¿Ľ
    -0.08
    è§Ĥ念
    -0.08
    drm
    -0.08
     оÑĦоÑĢмлен
    -0.08
    åĦ¿
    -0.08
    wayne
    -0.08
    wers
    -0.08
    POSITIVE LOGITS
    æĿĥçĽĬ
    0.09
    tps
    0.09
    çŃ·
    0.09
     sag
    0.09
    inks
    0.09
    /gl
    0.09
    çĽį
    0.09
     dojo
    0.09
     Phelps
    0.09
     Forever
    0.09
    Activations Density 0.041%

    No Known Activations