© 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. 31598
    Prev
    Next
    INDEX
    Explanations

    as a comparison or role

    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
     favourite
    -0.09
    å¸ij
    -0.09
    ç±¼
    -0.08
    åįķ项
    -0.08
    emb
    -0.08
    æĩĭ
    -0.08
     Celt
    -0.08
    å½ĵæĪij们
    -0.08
    éĶ¦æłĩ
    -0.08
    åIJĦèĩª
    -0.08
    POSITIVE LOGITS
     an
    0.13
     a
    0.10
    ä¹Łæĺ¯ä¸Ģ个
    0.10
    åħīçݯ
    0.10
    æĺ¯ä¸ĢåĢĭ
    0.09
    çļĦä¸Ģ个
    0.09
    æĺ¯ä¸Ģ个
    0.09
    ä¸Ģæŀļ
    0.09
    ä¼ļéķ¿
    0.09
    äºĨä¸Ģ个
    0.08
    Activations Density 0.188%

    No Known Activations