© 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. 16783
    Prev
    Next
    INDEX
    Explanations

    Penney, NeimanMarcus, J.C. Bradford, Boehringer Ingelheim, PricewaterhouseCoopers, HSBC

    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
    è®°èĢħåľ¨
    -0.10
    æľ¬äºĭ
    -0.09
    寸
    -0.09
     Abed
    -0.09
    æī¼
    -0.09
    rypton
    -0.09
    æŁłæª¬
    -0.09
    bris
    -0.08
    theid
    -0.08
    /as
    -0.08
    POSITIVE LOGITS
    åħ¬åı¸çļĦ
    0.11
    åħ¬åı¸
    0.11
     corporation
    0.10
     Corporation
    0.10
     company
    0.09
    éĽĨåĽ¢
    0.09
     Fortune
    0.09
    åħ¬åı¸åľ¨
    0.09
    ISA
    0.08
     fortune
    0.08
    Activations Density 0.245%

    No Known Activations