© 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. 59337
    Prev
    Next
    INDEX
    Explanations

    parties in legal contexts

    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
    为æ°ij
    -0.12
    yo
    -0.09
    té
    -0.08
    Dependency
    -0.08
    åĪļ
    -0.08
    .deep
    -0.08
    åĩĢ
    -0.08
    帮ä»ĸ
    -0.07
    ente
    -0.07
    æ°ijæĦı
    -0.07
    POSITIVE LOGITS
    åIJĦæĸ¹
    0.23
    å½ĵäºĭ人
    0.18
    åıĮæĸ¹
    0.17
    ä¸īæĸ¹
    0.17
     parties
    0.16
    å¤ļæĸ¹
    0.15
     Parties
    0.14
    å½ĵäºĭ
    0.14
    ä¸Ģæĸ¹
    0.13
    ä¸Ĭä¸ĭ游
    0.13
    Activations Density 0.051%

    No Known Activations