© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 34291
    Prev
    Next
    INDEX
    Explanations

    Jewish, woman, Brazilian identity markers

    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
    Not in Any Lists

    No Comments

    Negative Logits
    çĨŁæĤīçļĦ
    -0.10
    æĨ§
    -0.10
    çİ©ç¬ij
    -0.09
    åĵªæĢķæĺ¯
    -0.09
    ç²¥
    -0.09
    æĢĿãģĦåĩº
    -0.09
    ä¸įæĿ¥
    -0.09
    åĵªæĢķ
    -0.08
    åĻ±
    -0.08
    лев
    -0.08
    POSITIVE LOGITS
    æľīç§į
    0.10
    åĬŀ
    0.10
    pas
    0.09
    å¼ĢåĬŀ
    0.08
     UNITED
    0.08
    第ä¸Ģ
    0.08
    åºĶæĶ¶è´¦æ¬¾
    0.08
     bü
    0.08
    çıŃéķ¿
    0.08
    å¯¹æľªæĿ¥
    0.08
    Activations Density 0.047%

    No Known Activations