© 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. 12298
    Prev
    Next
    INDEX
    Explanations

    spotted, tailed, faced, striped

    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
    ski
    -0.08
    ings
    -0.08
    çļĦæ¦Ĥ念
    -0.08
     schedules
    -0.08
    pow
    -0.08
    åľ£åľ°
    -0.08
    ä¹ĭéĻħ
    -0.08
    ró
    -0.08
    çļĦèĦļæŃ¥
    -0.07
    å·®
    -0.07
    POSITIVE LOGITS
    羣è¯ļ
    0.11
    ä¸¥æł¼æĮīçħ§
    0.10
    ëĿ½
    0.09
     thá»ķ
    0.09
    ç»ı纪人
    0.09
    è¦ģ好好
    0.09
    ä¸įè´Ł
    0.09
    ä¸ĢåĪĩéĥ½æĺ¯
    0.09
    缮çļĦæĺ¯
    0.09
    ARATION
    0.09
    Activations Density 0.021%

    No Known Activations