© 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. 7818
    Prev
    Next
    INDEX
    Explanations

    seeking X to do Y

    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
    ç£ķ
    -0.10
     gotta
    -0.09
    æij¸ç´¢
    -0.09
    ä¸įä¸ĭ
    -0.09
     ith
    -0.09
    ĥĿ
    -0.09
     trick
    -0.09
    dal
    -0.09
    çļĦåŃ¦ä¹ł
    -0.08
    æĦİ
    -0.08
    POSITIVE LOGITS
    éŀĺ
    0.10
    éľģ
    0.09
    å°¾
    0.09
    读åIJİ
    0.08
    æĸĹ
    0.08
    弯
    0.08
    尾巴
    0.08
    ä¹ĭéĻħ
    0.08
    æĤ£
    0.08
    åĿı
    0.08
    Activations Density 0.060%

    No Known Activations