© 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. 26279
    Prev
    Next
    INDEX
    Explanations

    some of the

    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
    ä¸ĢæĬ¹
    -0.12
    ä¸Ģäºĭ
    -0.10
    ä¸Ģ群
    -0.09
    寥
    -0.09
    çĶ¨åĬĽ
    -0.09
     COPYRIGHT
    -0.09
    ä¸ĢèĪ¬
    -0.09
    踵
    -0.09
    ä¿©
    -0.09
    ä¸Ģåı¥
    -0.09
    POSITIVE LOGITS
    çĶļèĩ³æĺ¯
    0.10
    çī¹åĪ«æĺ¯åľ¨
    0.08
    侧éĿ¢
    0.08
    çīºçī²
    0.08
    ÙĦ
    0.08
    ä¼¼
    0.08
    çĶļèĩ³
    0.08
    失
    0.08
    åħ¶ä»ĸçļĦ
    0.08
    æĹģ
    0.08
    Activations Density 0.113%

    No Known Activations