© 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. 60951
    Prev
    Next
    INDEX
    Explanations

    Republican Party

    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
    å¾·æĭī
    -0.10
    åĴĮåıijå±ķ
    -0.10
    s
    -0.09
    åIJĦ家
    -0.09
    izi
    -0.08
    æªĹ
    -0.08
    å¿ĥå¢ĥ
    -0.08
    åIJĦåĽ½
    -0.08
    trag
    -0.08
    æĺŁ
    -0.08
    POSITIVE LOGITS
    aska
    0.10
     зан
    0.09
    кова
    0.08
     wr
    0.08
     Kushner
    0.08
    rene
    0.08
    \Abstract
    0.08
     каж
    0.08
    绥
    0.08
    欲
    0.08
    Activations Density 0.011%

    No Known Activations