© 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. 29457
    Prev
    Next
    INDEX
    Explanations

    legislative bodies

    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
    æīĢåľ¨
    -0.11
    档次
    -0.10
    å¿ĥæĦı
    -0.09
    è¡ĮåĬ¨è®¡åĪĴ
    -0.09
    TOR
    -0.09
    æĺ¯éĿŀ
    -0.09
    å¤ĸå½¢
    -0.09
     |_|
    -0.08
    ä½ĵåĨħ
    -0.08
    åijĺ
    -0.08
    POSITIVE LOGITS
    że
    0.09
    å·¨æĺŁ
    0.09
    åѤåĦ¿
    0.08
    åĵij
    0.08
    tester
    0.08
    loor
    0.08
    æİĴè¡Į
    0.08
    ç°¸
    0.08
    orta
    0.08
    fter
    0.08
    Activations Density 0.007%

    No Known Activations