© 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. 64055
    Prev
    Next
    INDEX
    Explanations

    congestive or congested

    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
    acie
    -0.11
     filib
    -0.10
    hood
    -0.10
    ä¸Ģ举
    -0.09
    ç¿ķ
    -0.09
    éĻ¢éķ¿
    -0.09
    aceous
    -0.09
    们
    -0.09
    å°Ŀ
    -0.09
    罡
    -0.09
    POSITIVE LOGITS
    ingly
    0.11
     Catal
    0.09
    ä¸įåłª
    0.08
    大å±Ģ
    0.08
    liner
    0.08
    ured
    0.08
    lac
    0.08
    åľ°å¸¦
    0.08
    RICT
    0.08
    sit
    0.08
    Activations Density 0.018%

    No Known Activations