© 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. 60756
    Prev
    Next
    INDEX
    Explanations

    company business team

    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
     themselves
    -0.12
     powstaÅĤ
    -0.09
    满äºĨ
    -0.09
    塬
    -0.09
    èµ·æĿ¥
    -0.09
     اÙĦÙħج
    -0.09
    åĿıäºĨ
    -0.08
    ık
    -0.08
    icom
    -0.08
    åīįç½®
    -0.08
    POSITIVE LOGITS
    æĤ¨çļĦåŃ©åŃIJ
    0.10
    çļĦæķ´ä½ĵ
    0.09
     or
    0.09
    's
    0.09
    åħ·ä½ĵæĥħåĨµ
    0.08
    åĽłä¸ºä½ł
    0.08
    çļĦ羣å®ŀæĢ§
    0.08
     your
    0.08
     situation
    0.08
    绶
    0.08
    Activations Density 0.135%

    No Known Activations