© 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. 63919
    Prev
    Next
    INDEX
    Explanations

    that introduces a defining clause

    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
    è¿ĺä¸įå¤Ł
    -0.09
    ouv
    -0.09
    è°İ
    -0.08
    éĿŀ常çļĦ
    -0.08
    .cli
    -0.08
    ç«
    -0.08
    wis
    -0.08
    éĿ¢åŃĶ
    -0.08
    _FP
    -0.08
    ars
    -0.08
    POSITIVE LOGITS
    åıĹ欢è¿İ
    0.09
    ãģĭãģijãģ¦
    0.09
    ucc
    0.09
    WARE
    0.09
    éĹªéĹª
    0.09
    æ£
    0.09
     влад
    0.09
    eded
    0.09
    纪
    0.09
    æݨ
    0.08
    Activations Density 0.058%

    No Known Activations