© 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. 47466
    Prev
    Next
    INDEX
    Explanations

    hockey league or cup

    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
    è´Ŀ
    -0.10
    çľ·
    -0.10
    åįģåŃĹ
    -0.10
    èijµ
    -0.09
    è²Ŀ
    -0.09
    æĭĹ
    -0.09
     Jah
    -0.08
     Canter
    -0.08
    æľīæĦıä¹ī
    -0.08
    轸
    -0.08
    POSITIVE LOGITS
    inks
    0.08
    å·¥ä½ľä¼ļè®®
    0.08
    éĽį
    0.08
    æ¹Ħ
    0.08
    ALA
    0.08
    istine
    0.08
    éĻ¡
    0.08
    oron
    0.08
    ä¸įçĶ¨
    0.08
    ç³Ĺ
    0.08
    Activations Density 0.117%

    No Known Activations