© 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. 6102
    Prev
    Next
    INDEX
    Explanations

    Salvadoran or Salvador Mas

    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
    SqlParameter
    -0.10
    为人
    -0.09
    çĽİ
    -0.09
    ä¸ĩæĪ·
    -0.09
    èij©
    -0.09
    ÑĥÑĩа
    -0.08
    éħ¥
    -0.08
    ched
    -0.08
    ä¸į该
    -0.08
    .Paths
    -0.08
    POSITIVE LOGITS
    andom
    0.10
    fully
    0.10
    mand
    0.09
    èµİ
    0.09
     Busy
    0.09
    à¸ģà¸ģ
    0.09
    arez
    0.09
    ideo
    0.09
     deeds
    0.08
    æĶ¥
    0.08
    Activations Density 0.015%

    No Known Activations