© 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. 26064
    Prev
    Next
    INDEX
    Explanations

    at the expense of

    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
    éĥ½ä¸įæķ¢
    -0.09
    æĸĩåĮĸä¼łæĴŃ
    -0.09
    çĽ¸ä¼ł
    -0.09
    西äºļ
    -0.09
    Subtitle
    -0.09
    åıĭ好
    -0.09
    èģĮ
    -0.09
    çIJ¨
    -0.09
    adro
    -0.09
    çĶ¸
    -0.08
    POSITIVE LOGITS
    çīºçī²
    0.18
    çīº
    0.14
    代价
    0.13
    çĬ
    0.12
     detriment
    0.11
     sacrifice
    0.11
    .SDK
    0.10
     sacrificing
    0.10
     sacrific
    0.10
     fors
    0.10
    Activations Density 0.191%

    No Known Activations