© 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. 6234
    Prev
    Next
    INDEX
    Explanations

    win over, win the, win did, win Blazers

    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¿Ļä¹Īå¤ļå¹´
    -0.10
    ä¸ĩä¸Ģ
    -0.10
    åįĥå¹´
    -0.10
    ä¹Łæĺ¯å¦ĤæѤ
    -0.10
    åĪĽ
    -0.10
    åħĪè¿Ľåįķä½į
    -0.10
    å°±æĺ¯è¿Ļæł·
    -0.09
    å°ijäºĨ
    -0.09
    å°Ĩ继ç»Ń
    -0.09
    åįģå¹´åīį
    -0.09
    POSITIVE LOGITS
    éĢĨè¢Ń
    0.13
    æīŃ转
    0.12
    æĮ½åĽŀ
    0.11
    è¡¥
    0.10
    åĬłä»¥
    0.10
    åIJİæĿ¥
    0.10
    æģ°æģ°
    0.09
    åıįèĢĮ
    0.09
    便
    0.09
    éĢĨ转
    0.09
    Activations Density 0.040%

    No Known Activations