© 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. 8733
    Prev
    Next
    INDEX
    Explanations

    bowling action and pace

    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
    éĹ¹
    -0.10
    åIJ¦
    -0.09
    ãģĹãģ¾
    -0.09
    éĢļ讯
    -0.09
    离å¼ĢäºĨ
    -0.09
    æı´
    -0.09
    ä¸įåıĹ
    -0.09
    ä¸į认è¯Ĩ
    -0.09
    åİ»çľĭ
    -0.09
    æĹĹèĪ°
    -0.09
    POSITIVE LOGITS
    ä¸ĢçĽ´åľ¨
    0.09
    rovers
    0.09
    岬
    0.09
    线ä¸Ĭ
    0.09
    å¡ij
    0.09
    оваÑĢ
    0.08
    /pg
    0.08
    åľ°æĸ¹æĶ¿åºľ
    0.08
    æĻ¯
    0.08
    å»ī
    0.08
    Activations Density 0.092%

    No Known Activations