© 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. 7779
    Prev
    Next
    INDEX
    Explanations

    material qualities

    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
    éľ²
    -0.11
    æ´¾
    -0.10
    对éĿ¢
    -0.10
    款
    -0.09
     bath
    -0.09
    ä¸ĢæīĢ
    -0.09
    çļĦä¹IJ趣
    -0.09
    æĦıä¹īä¸ĬçļĦ
    -0.09
    éĴĬ
    -0.09
     Bath
    -0.08
    POSITIVE LOGITS
    èĢIJçĶ¨
    0.10
    稳å®ļçļĦ
    0.09
    تÙĪر
    0.09
    åĪ°åºķæĺ¯
    0.09
     Pix
    0.09
    å¥ļ
    0.09
    aling
    0.09
    æ¢Ŀ
    0.09
    swire
    0.08
     диÑģк
    0.08
    Activations Density 0.039%

    No Known Activations