© 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. 47605
    Prev
    Next
    INDEX
    Explanations

    elections and incumbents

    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
    escort
    -0.10
    éĻĽä¸ĭ
    -0.09
    åIJĦçľģ
    -0.09
    ä¸ĸçķĮåIJĦåĽ½
    -0.09
    ä¼Łå¤§çļĦ
    -0.09
    è¶ĬæĿ¥è¶Ĭ
    -0.08
    jong
    -0.08
    éĻĽ
    -0.08
     malaysia
    -0.08
    ç¥ŀå·ŀ
    -0.08
    POSITIVE LOGITS
     incumbent
    0.12
    å½ĵåľ°äºº
    0.11
    èĭ¦
    0.10
    åħ¨åİ¿
    0.10
    æĿijæ°ij
    0.10
    è´¿
    0.10
    ç«ŀéĢī
    0.09
    åĽ¢ç»ĵ
    0.09
     incumb
    0.09
    åħļ
    0.09
    Activations Density 0.124%

    No Known Activations