© 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. 6131
    Prev
    Next
    INDEX
    Explanations

    study of Bible

    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
    ized
    -0.10
    ÃŃt
    -0.09
    缪
    -0.09
    oj
    -0.08
    isan
    -0.08
    èĥª
    -0.08
    æħ·æħ¨
    -0.08
     elaborate
    -0.08
    pie
    -0.08
    éŀĭåŃIJ
    -0.08
    POSITIVE LOGITS
    æĥļ
    0.10
    erdem
    0.09
    rieb
    0.09
    td
    0.09
    fleet
    0.09
    ái
    0.09
    ä¼Ļä¼´
    0.08
    ItemImage
    0.08
    angler
    0.08
    AndWait
    0.08
    Activations Density 0.018%

    No Known Activations