© 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. 16659
    Prev
    Next
    INDEX
    Explanations

    performing arts

    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
    æľ´
    -0.10
    åĩ«
    -0.10
    PILE
    -0.09
    ÑĢÑĥÑĩ
    -0.09
    erry
    -0.09
    à¸Ĺา
    -0.09
    为é¦ĸçļĦ
    -0.09
    è±³
    -0.09
    acas
    -0.09
    oral
    -0.08
    POSITIVE LOGITS
    åĬłçĽĸ
    0.09
    表æ¼Ķ
    0.09
    formance
    0.09
    éĢ®
    0.09
    alent
    0.09
    èĪŀåı°ä¸Ĭ
    0.08
    .perform
    0.08
    å´´
    0.08
    ative
    0.08
    çĭ¬è§Ĵ
    0.08
    Activations Density 0.016%

    No Known Activations