© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 5678
    Prev
    Next
    INDEX
    Explanations

    election results, votes, ballots

    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
    wart
    -0.09
    éĵ¢
    -0.09
    пÑĢакÑĤи
    -0.09
     пÑĢакÑĤиÑĩ
    -0.08
    建åĨĽ
    -0.08
    åĬŀ好
    -0.08
    åĩºè¡Į
    -0.08
     Lor
    -0.08
     stakes
    -0.08
    Rare
    -0.08
    POSITIVE LOGITS
    åĮ¿åIJį
    0.11
    åĩłå¼ł
    0.10
    é©¿
    0.10
     votes
    0.10
    表åĨ³
    0.10
     ballots
    0.10
    æĬķ票
    0.10
     Vote
    0.10
    æĬķ
    0.10
    ä¸Ģå¼ł
    0.10
    Activations Density 0.089%

    No Known Activations