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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 51467
    Prev
    Next
    INDEX
    Explanations

    next or previous event/item

    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
     плоÑħо
    -0.09
     ÐĴоз
    -0.09
    åij¨åĽ´çļĦ
    -0.09
    åij¨åĽ´
    -0.09
    rias
    -0.09
    æļ®
    -0.08
    èĿī
    -0.08
    ä¸ĭå·´
    -0.08
    ses
    -0.08
    ipel
    -0.08
    POSITIVE LOGITS
    æĪijè¦ģ
    0.09
     trick
    0.09
    istent
    0.08
    第ä¸īèĬĤ
    0.08
    æĪij羣çļĦ
    0.08
    -solid
    0.08
    away
    0.08
    isto
    0.08
    æĪijä¼ļ
    0.08
    飧æĢ§
    0.08
    Activations Density 0.020%

    No Known Activations