© 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. 40371
    Prev
    Next
    INDEX
    Explanations

    lawyer

    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
    pak
    -0.09
    loth
    -0.08
    arium
    -0.08
    å·´æĭī
    -0.08
    огÑĢам
    -0.08
    ç¾İ好çĶŁæ´»
    -0.08
    å¼Ħå¾Ĺ
    -0.08
    ansk
    -0.08
    ouflage
    -0.08
    outh
    -0.08
    POSITIVE LOGITS
    /legal
    0.12
    æ³ķåѦ
    0.10
     luáºŃt
    0.10
    å¾ĭå¸Ī
    0.10
     lawyer
    0.10
    æ³ķå¾ĭ
    0.09
    /pol
    0.09
     legal
    0.09
     criminal
    0.09
    -pol
    0.09
    Activations Density 0.124%

    No Known Activations