© 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. 6134
    Prev
    Next
    INDEX
    Explanations

    musicians and composers

    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
    åįī
    -0.09
    åĪ°åºķæĺ¯
    -0.09
     pure
    -0.09
    è¦ģä¹Ī
    -0.09
    enthal
    -0.09
    åĪ¨
    -0.09
    iso
    -0.09
    èIJ
    -0.09
    _Entry
    -0.09
    蹬
    -0.08
    POSITIVE LOGITS
    nes
    0.10
    å¼¢
    0.09
    åħŃ大
    0.09
    åħįç¨İ
    0.09
    lien
    0.08
    æ½®
    0.08
    LOW
    0.08
    éĺµèIJ¥
    0.08
    iams
    0.08
    kel
    0.08
    Activations Density 0.236%

    No Known Activations