© 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. 582
    Prev
    Next
    INDEX
    Explanations

    news wire services

    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
    amera
    -0.11
    çĪ±å¥½èĢħ
    -0.09
    ä¸ļä½Ļ
    -0.09
    壯
    -0.08
    æī¿
    -0.08
    ç³ł
    -0.08
    wart
    -0.08
    åijĭ
    -0.08
    éĩĿ
    -0.08
    amon
    -0.08
    POSITIVE LOGITS
    ä¸į失
    0.10
    åľ¨ä»ĸçļĦ
    0.09
    å¼Ģåĩº
    0.09
    é£ı
    0.09
    uced
    0.08
    ูล
    0.08
    åŀĨ
    0.08
     mischief
    0.08
     maxx
    0.08
    virt
    0.08
    Activations Density 0.001%

    No Known Activations