© 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. 6062
    Prev
    Next
    INDEX
    Explanations

    only / exclusively

    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
    ë¡Ģ
    -0.11
    rieg
    -0.09
    åĬ²
    -0.09
    夺
    -0.09
    rone
    -0.09
    ลาà¸Ķ
    -0.09
    etag
    -0.09
    åĭģ
    -0.09
    egis
    -0.08
     goggles
    -0.08
    POSITIVE LOGITS
    ç»Ŀä¸į
    0.11
    è¿Ļæł·æīįèĥ½
    0.10
    æİ¥æīĭ
    0.10
    æºIJ头
    0.09
     Ups
    0.09
    ups
    0.09
    -only
    0.09
    ä¸įä½İäºİ
    0.09
    åŁºæľ¬ä¸Ĭéĥ½
    0.08
    ä¹IJæĦı
    0.08
    Activations Density 0.088%

    No Known Activations