© 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. 24118
    Prev
    Next
    INDEX
    Explanations

    return or back

    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
    COPE
    -0.10
    èĪģ
    -0.10
    éĺģ
    -0.09
    çļĦä¼Łå¤§
    -0.09
    å¸ĮæľĽèĥ½
    -0.09
    å¿Ļ
    -0.08
    çļĦ妻åŃIJ
    -0.08
    æħ¢æħ¢
    -0.08
     Harold
    -0.08
    æħ¢æħ¢çļĦ
    -0.07
    POSITIVE LOGITS
    åĨį次
    0.17
    åĨįæĿ¥
    0.12
    åĨį度
    0.11
     Ñģнова
    0.10
    åĽŀåİ»
    0.10
     again
    0.09
     Dirty
    0.09
    åıĪä¸Ģ次
    0.09
    /antlr
    0.09
    -repeat
    0.09
    Activations Density 0.022%

    No Known Activations