© 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. 63923
    Prev
    Next
    INDEX
    Explanations

    United States cities

    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
    thon
    -0.11
    uv
    -0.09
    fully
    -0.09
    ral
    -0.09
     swing
    -0.08
    éĦŀ
    -0.08
    tone
    -0.08
    å¿ĥ头
    -0.08
     NYPD
    -0.08
    ç´IJ
    -0.08
    POSITIVE LOGITS
    éļĶçĥŃ
    0.11
    odash
    0.10
    çĥŃæIJľ
    0.10
    æĪª
    0.09
    害
    0.09
    æķĻä¼ļ
    0.09
    arium
    0.09
    roman
    0.09
    æĺı
    0.09
    fall
    0.08
    Activations Density 0.017%

    No Known Activations