© 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. 59204
    Prev
    Next
    INDEX
    Explanations

    species, varieties, or types

    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
    使æĪij
    -0.09
    èŃ½
    -0.09
    orda
    -0.09
    åı¯æĥ³èĢĮçŁ¥
    -0.08
    _PRIMARY
    -0.08
    æ¯į亲
    -0.08
    çį¾
    -0.08
    ä¸Ģ天
    -0.08
     sme
    -0.08
    è²Ĥ
    -0.08
    POSITIVE LOGITS
    æѤ类
    0.17
    è¿Ļç±»
    0.15
    ãģĵãģĨãģĦãģĨ
    0.15
    类似çļĦ
    0.14
     such
    0.13
    è¿Ļç§įäºĭæĥħ
    0.12
     ÑĤакого
    0.11
    å¾Ģå¾Ģ
    0.11
    è¿Ļæł·çļĦ
    0.11
    å¾Ģå¾Ģä¼ļ
    0.10
    Activations Density 1.030%

    No Known Activations