© 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. 47547
    Prev
    Next
    INDEX
    Explanations

    the following proper noun

    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
    tá
    -0.11
    sil
    -0.09
    vÃŃ
    -0.09
    篮
    -0.09
    충
    -0.09
    oste
    -0.08
    (super
    -0.08
    ç½ļ
    -0.08
    lien
    -0.08
     Insider
    -0.08
    POSITIVE LOGITS
    åģļä¸Ģ个
    0.10
     month
    0.10
    æµĵæµĵçļĦ
    0.09
    åħ¨é¢Ŀ
    0.09
    æŃĮ声
    0.09
    èķŀ
    0.08
    管çIJĨå±Ģ
    0.08
    å¦Ĥæŀľæĺ¯
    0.08
    äºĨ解ä¸Ģä¸ĭ
    0.08
    è¿ľ
    0.08
    Activations Density 0.173%

    No Known Activations