© 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. 16616
    Prev
    Next
    INDEX
    Explanations

    countries and military forces

    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
    æĪĸå¤ļ
    -0.10
    redd
    -0.09
    å²ĺ
    -0.09
    è°Ĺ
    -0.09
    æĪijåİ»
    -0.09
    åĢ¾åIJ¬
    -0.09
    èĴŁ
    -0.09
    æĦŁ
    -0.08
     oneself
    -0.08
    ç¾İåĽ½äºº
    -0.08
    POSITIVE LOGITS
    éĺµèIJ¥
    0.12
    è¿Ļè¾¹
    0.10
    zan
    0.09
    èµ°
    0.09
    åľ¨è¿Ļ个
    0.08
    ardin
    0.08
    ä¸ĭçıŃ
    0.08
     Miche
    0.08
     effort
    0.08
    æĬĢ
    0.08
    Activations Density 0.092%

    No Known Activations