© 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. 803
    Prev
    Next
    INDEX
    Explanations

    football clubs

    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
    建档ç«ĭåį¡
    -0.09
    åIJĦè¡Į
    -0.08
    eday
    -0.08
    æ··
    -0.08
    çľĭä»ĸ
    -0.08
    åħ¨éķĩ
    -0.08
    æĸ¤
    -0.08
    å°ijä¸įäºĨ
    -0.08
    eshire
    -0.08
     Orthodox
    -0.08
    POSITIVE LOGITS
    èķ²
    0.09
    ä¸Ģ头
    0.09
     Hv
    0.09
    NSURL
    0.09
    rü
    0.09
    ç±³é¥Ń
    0.09
    ç´«
    0.08
    owitz
    0.08
    ÑĩÑĥв
    0.08
    顶
    0.08
    Activations Density 0.032%

    No Known Activations