© 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. 26399
    Prev
    Next
    INDEX
    Explanations

    vote and voter propositions

    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
    稽
    -0.12
    è·»
    -0.09
    å¾½
    -0.09
    çķĮ第ä¸Ģ
    -0.09
     наÑģÑĤоÑı
    -0.09
     eql
    -0.09
    ä¸Ģ家人
    -0.09
    æĭ¯
    -0.09
    AAP
    -0.09
    æѦèѦ
    -0.09
    POSITIVE LOGITS
    æĬķ票
    0.13
    表åĨ³
    0.13
     vote
    0.13
     voter
    0.12
     voting
    0.12
     ballots
    0.12
     referendum
    0.12
     Vote
    0.11
    Vote
    0.11
     votes
    0.11
    Activations Density 0.116%

    No Known Activations