© 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. 6159
    Prev
    Next
    INDEX
    Explanations

    incorporate or add

    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
     возд
    -0.10
    åĬĽæ°Ķ
    -0.09
    ility
    -0.09
    åĪ¹è½¦
    -0.09
    ä¸Ĭä¼ł
    -0.09
     Protective
    -0.09
    纷纷
    -0.08
    没äºĭ
    -0.08
    è¿Ļä¸ĢåĪĩ
    -0.08
    æĺ¯æľĢ好çļĦ
    -0.08
    POSITIVE LOGITS
    æݺ
    0.10
     Incorpor
    0.10
    INC
    0.10
    çĤ¹ç¼Ģ
    0.10
     incorporate
    0.09
     daily
    0.09
     everyday
    0.09
    æĹ¥å¸¸
    0.09
     incorpor
    0.09
    åł°
    0.08
    Activations Density 0.044%

    No Known Activations