© 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. 29470
    Prev
    Next
    INDEX
    Explanations

    always boring, increasingly important

    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
    ä½łçİ°åľ¨
    -0.09
    ä½łä¼ļåıijçİ°
    -0.09
    æĬµæĬĹ
    -0.09
    Ñīи
    -0.09
    åı¯æĢľ
    -0.08
    ä¸Ģæµģ
    -0.08
    å¸ļ
    -0.08
    ä¸ĢåĪĩéĥ½æĺ¯
    -0.08
    åĻ¤
    -0.08
    .getSelection
    -0.08
    POSITIVE LOGITS
    æĪij对
    0.32
    对æĪijæĿ¥è¯´
    0.31
    åľ¨æĪijçļĦ
    0.31
    æĪijçļĦ
    0.30
     my
    0.29
    æĪij
    0.29
     myself
    0.29
    æĪijèĩªå·±
    0.29
    äºĨæĪijçļĦ
    0.28
    使æĪij
    0.28
    Activations Density 0.840%

    No Known Activations