© 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. 60718
    Prev
    Next
    INDEX
    Explanations

    Cardinals, Newman, Sinatra

    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
     Sandy
    -0.11
    etch
    -0.10
    abl
    -0.09
    ider
    -0.09
    blem
    -0.09
     Keller
    -0.08
    nbsp
    -0.08
    old
    -0.08
    itution
    -0.08
    人éĢī
    -0.08
    POSITIVE LOGITS
     обÑĢазом
    0.10
    -minded
    0.10
    ITY
    0.10
    IGNED
    0.09
    èĦijåŃIJéĩĮ
    0.09
    å¸ľ
    0.09
    ãģ¹ãģį
    0.09
    upo
    0.09
    ä»ķ
    0.09
    çŀŃ
    0.09
    Activations Density 0.003%

    No Known Activations