© 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. 59263
    Prev
    Next
    INDEX
    Explanations

    musical theatre and opera

    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
    æ¯Ľ
    -0.09
    иÑĢов
    -0.09
    æĤłæĤł
    -0.08
    orpion
    -0.08
    寺
    -0.08
    æĩĴ
    -0.08
    inger
    -0.08
    Ợ
    -0.08
    èĶij
    -0.08
    /apt
    -0.08
    POSITIVE LOGITS
    亢
    0.10
    åĥ¦
    0.09
    ä¸įåĬ¨
    0.09
    semb
    0.09
    ë¹Ļ
    0.08
    大éħĴåºĹ
    0.08
    åѦéĹ®
    0.08
    æ±Łæ·®
    0.08
    躬
    0.08
    趾
    0.08
    Activations Density 0.075%

    No Known Activations