© 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. 59193
    Prev
    Next
    INDEX
    Explanations

    establishment and institutions

    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
    亲
    -0.09
    ç½ijåıĭ
    -0.09
    çľĩ
    -0.09
    åºĸ
    -0.09
    åħĪ导
    -0.09
    åĽ½äºº
    -0.08
    èĨ¨
    -0.08
    LT
    -0.08
    ĥĿ
    -0.08
    anske
    -0.08
    POSITIVE LOGITS
    主æµģ
    0.16
    ä½ĵåĪ¶
    0.14
    ä¼łç»ŁçļĦ
    0.14
    æĿĥå¨ģ
    0.13
    ä¼łç»Ł
    0.12
     mainstream
    0.12
    å®ĺæĸ¹
    0.12
    çĽij管éĥ¨éŨ
    0.11
    å½ĵå±Ģ
    0.11
    èħIJ
    0.11
    Activations Density 0.096%

    No Known Activations