© 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. 59342
    Prev
    Next
    INDEX
    Explanations

    Roman history and empire

    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
    ä¹Łæĺ¯å¾Ī
    -0.08
    å°ijçĪ·
    -0.08
    缴èIJ¥
    -0.08
    离
    -0.08
    便
    -0.08
    人éĢł
    -0.08
    Wo
    -0.07
     fest
    -0.07
    æĶ¾åģĩ
    -0.07
     Pac
    -0.07
    POSITIVE LOGITS
    å¢Ļä½ĵ
    0.10
    olut
    0.09
     Fulton
    0.09
    åŁºè¾ħ
    0.09
     kem
    0.09
    antium
    0.09
    iman
    0.09
     Rudd
    0.08
    侮辱
    0.08
     Gül
    0.08
    Activations Density 0.035%

    No Known Activations