© 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. 60555
    Prev
    Next
    INDEX
    Explanations

    election results and political leanings

    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
    èĵŁ
    -0.09
    麾
    -0.09
    ä¸Ģæŀ¶
    -0.09
    éħª
    -0.08
    isp
    -0.08
    åѦéĹ®
    -0.08
    ocrates
    -0.08
    ูà¹ī
    -0.08
    .df
    -0.08
    绪
    -0.08
    POSITIVE LOGITS
    zen
    0.09
    åı¯æĥ³èĢĮçŁ¥
    0.09
    濯
    0.09
    æĹ¶æ®µ
    0.09
    å¾®å¦Ļ
    0.08
     Sheep
    0.08
    åı¯éĿłæĢ§
    0.08
    æݾ
    0.08
    éĽĨè£ħ
    0.08
    æ¼Ķä¹ł
    0.08
    Activations Density 0.016%

    No Known Activations