© 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. 26163
    Prev
    Next
    INDEX
    Explanations

    ballet and dance

    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
    å¡ŀ
    -0.11
    illon
    -0.09
    æ¯ı个æľĪ
    -0.09
    è¦Ĩ
    -0.09
    笼
    -0.09
    Emitter
    -0.08
    оÑĤов
    -0.08
    smith
    -0.08
    issen
    -0.08
    åħ¨äº§ä¸ļéĵ¾
    -0.08
    POSITIVE LOGITS
    èĪŀè¹Ī
    0.16
    èĪŀ
    0.14
    è·³èĪŀ
    0.13
     Ballet
    0.12
     dancer
    0.12
     ballet
    0.12
    dance
    0.12
     danced
    0.11
     dance
    0.11
    åĬ¨ä½ľ
    0.11
    Activations Density 0.052%

    No Known Activations