© 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. 5995
    Prev
    Next
    INDEX
    Explanations

    as a

    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
    Not in Any Lists

    No Comments

    Negative Logits
    åħ«åŃĹ
    -0.08
    çĶŁåij½çļĦ
    -0.08
    åıŃ
    -0.08
    æľīæĽ´å¤ļçļĦ
    -0.08
    çIJĨä¼ļ
    -0.07
    人们çļĦ
    -0.07
    æīĢåľ¨çļĦ
    -0.07
    ä»»æĦı
    -0.07
    æīĢåģļçļĦ
    -0.07
    åĢŁåı£
    -0.07
    POSITIVE LOGITS
     an
    0.20
     a
    0.20
    ä¸Ģ个å°ı
    0.17
    ä¸Ģ个
    0.15
    ä¸Ģ座
    0.14
    ä¸Ģ个èģĮä¸ļ
    0.14
    ä¸Ģ份
    0.14
    ä¸Ģ个好çļĦ
    0.14
     sebuah
    0.13
    äºĨä¸Ģ份
    0.13
    Activations Density 2.149%

    No Known Activations