© 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. 19126
    Prev
    Next
    INDEX
    Explanations

    distributed systems and infrastructure

    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
    å·¥
    -0.09
    禹
    -0.08
    æĸĩç«łæĿ¥æºIJ
    -0.08
    æĪĴ
    -0.08
     spot
    -0.08
    تجا
    -0.08
    éĺģ
    -0.08
    å¾Ģäºĭ
    -0.07
    traits
    -0.07
    å¯Ł
    -0.07
    POSITIVE LOGITS
    æķ£å¸ĥ
    0.13
    åĪĨæķ£
    0.13
    éĩĩéĽĨ
    0.11
    楸
    0.10
     distributed
    0.10
    漪
    0.10
    distributed
    0.10
    åĪĨå¸ĥå¼ı
    0.10
    å¼ıçļĦ
    0.09
    æĢ§çļĦ
    0.09
    Activations Density 0.127%

    No Known Activations