© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 47653
    Prev
    Next
    INDEX
    Explanations

    and with others

    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
    Negative Logits
    åľ©
    -0.09
    çī§
    -0.09
    oft
    -0.09
     Anthrop
    -0.08
    oug
    -0.08
     ÑģÑĤол
    -0.08
    ä¸ĵä¸ļåĮĸ
    -0.08
    å¢ŀåĢ¼
    -0.08
    è¿İæĿ¥
    -0.08
    inc
    -0.08
    POSITIVE LOGITS
    åIJIJ
    0.10
    æ¼Ķ
    0.10
    娣
    0.10
    ä¸įåıĹ
    0.09
    稳
    0.09
    æݩ饰
    0.09
    éĶ¦ç»£
    0.09
    ä¸įè¦ģ太
    0.09
    åį°
    0.09
    主ä¸ļ
    0.09
    Activations Density 0.009%

    No Known Activations