© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 55996
    Prev
    Next
    INDEX
    Explanations

    banned from sports

    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
    åºľ
    -0.11
    æ¥Ķ
    -0.11
    éĵ°
    -0.10
    èµ°åħ¥
    -0.09
    飨
    -0.09
    寿åij½
    -0.09
    веÑĢ
    -0.09
    饺
    -0.09
    èij«èĬ¦
    -0.09
    -LAST
    -0.09
    POSITIVE LOGITS
    è¿IJåĬ¨åijĺ
    0.13
     doping
    0.12
    ä¸Ģ头
    0.11
     athletes
    0.10
    转ä¼ļ
    0.10
     athlete
    0.09
    åħ´å¥ĭ
    0.09
    è®Ńç»ĥ
    0.09
    åĨ²æ´Ĺ
    0.09
    ä¸Ŀä¸Ŀ
    0.09
    Activations Density 0.348%

    No Known Activations