© 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. 35020
    Prev
    Next
    INDEX
    Explanations

    voting, endorsements, election results, political campaigns

    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
    éĹ®éĹ®
    -0.09
    请大家
    -0.09
     nou
    -0.09
    辩论
    -0.09
    æ®Ĵ
    -0.08
    è¤Ĥ
    -0.08
    [loc
    -0.08
    æĥ°
    -0.08
    奸
    -0.08
     competition
    -0.08
    POSITIVE LOGITS
    æĶ¯æĮģ
    0.11
    åĪĨéĴŁå·¦åı³
    0.10
     favor
    0.10
    æĶ¯æı´
    0.10
    å·¦åı³
    0.10
    追éļı
    0.10
     favour
    0.09
    æĶ¯æĮģåĬĽåº¦
    0.09
     поддеÑĢжива
    0.09
    åĬ©åĬĽ
    0.09
    Activations Density 0.065%

    No Known Activations