© 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. 59323
    Prev
    Next
    INDEX
    Explanations

    leading and control

    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
    eus
    -0.09
    壮大
    -0.09
    被害
    -0.08
    ä¾Ĺ
    -0.08
    jee
    -0.08
    æĬ¥ä»ĩ
    -0.08
    erd
    -0.08
    éļ¾å¾Ĺ
    -0.08
    å¥¹åľ¨
    -0.07
    eder
    -0.07
    POSITIVE LOGITS
    çļĦä¸ĢåĪĩ
    0.10
    æīĢæľīæĥħèĬĤ
    0.10
    htable
    0.10
     ÑĢаÑģпол
    0.09
    opsis
    0.09
    spiel
    0.09
    دÙĨÙĬ
    0.09
    agged
    0.09
    å¼¥
    0.09
    enthal
    0.09
    Activations Density 0.003%

    No Known Activations