© 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. 6099
    Prev
    Next
    INDEX
    Explanations

    brotherhoods, keys, duos, twins

    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
    rase
    -0.10
    Fuse
    -0.09
    大æ´ĭ
    -0.09
    åħľ
    -0.09
    妨ç¢į
    -0.08
    åľ¨æĦı
    -0.08
    åŦ
    -0.08
    许
    -0.08
    å±Ĥå±Ĥ
    -0.08
    åģĥ
    -0.08
    POSITIVE LOGITS
    åıĮåıĮ
    0.14
    åıĮ
    0.12
    åħĦå¼Ł
    0.12
     twin
    0.12
     duo
    0.12
     pair
    0.11
     twins
    0.11
    åŃª
    0.11
    ä¿©
    0.11
    两个
    0.11
    Activations Density 0.170%

    No Known Activations