© 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. 64043
    Prev
    Next
    INDEX
    Explanations

    dance and related activities

    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
    ness
    -0.10
    ted
    -0.10
    ty
    -0.10
    èĽĭ
    -0.09
    TING
    -0.09
    ting
    -0.09
    ist
    -0.09
    ../../../
    -0.09
    nest
    -0.09
     оÑĤмеÑĤ
    -0.08
    POSITIVE LOGITS
    able
    0.11
    èµ·æĿ¥
    0.10
    ableObject
    0.09
    osas
    0.09
    ADVERTISEMENT
    0.09
    ë¡Ń
    0.09
    sticks
    0.09
    ABLE
    0.09
    lopedia
    0.09
     endregion
    0.08
    Activations Density 0.010%

    No Known Activations