© 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. 12271
    Prev
    Next
    INDEX
    Explanations

    Latin America

    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
    ingly
    -0.15
    ä¸įèµ·
    -0.10
    sei
    -0.09
    åŃIJéĩĮ
    -0.09
     Fargo
    -0.09
    vell
    -0.09
     sic
    -0.09
    ç¢ī
    -0.09
    hana
    -0.09
    绢
    -0.08
    POSITIVE LOGITS
    most
    0.12
    ized
    0.10
    ues
    0.10
    -speaking
    0.09
    ically
    0.09
    ised
    0.09
    qed
    0.09
    ization
    0.08
     Tiên
    0.08
    /or
    0.08
    Activations Density 0.006%

    No Known Activations