© 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. 47552
    Prev
    Next
    INDEX
    Explanations

    outsourcing firms

    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
    arro
    -0.11
    icult
    -0.09
    å¥ļ
    -0.09
     kino
    -0.09
     Cute
    -0.08
    ä¼ij
    -0.08
    mour
    -0.08
    ä¼ı
    -0.08
    amic
    -0.08
     GIF
    -0.08
    POSITIVE LOGITS
    å¤ĸåĮħ
    0.17
    æľįåĬ¡æ°´å¹³
    0.12
     outsourcing
    0.11
     services
    0.11
    æīĺ管
    0.11
     Outs
    0.11
    æľįåĬ¡
    0.11
    æľįåĬ¡ä¸ļ
    0.11
    代åĬŀ
    0.11
    çļĦæľįåĬ¡
    0.10
    Activations Density 0.096%

    No Known Activations