© 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. 59289
    Prev
    Next
    INDEX
    Explanations

    retail store names

    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
    仪
    -0.09
    æĪ¿ä¸ľ
    -0.09
    isia
    -0.08
    åħĪ导
    -0.08
    ushi
    -0.08
    steller
    -0.08
    abar
    -0.08
    \Collections
    -0.08
    ynes
    -0.08
    endra
    -0.08
    POSITIVE LOGITS
    æĪŁ
    0.10
    front
    0.09
    orman
    0.08
    橱
    0.08
    صÙĪÙĦ
    0.08
    åij¨åĪĬ
    0.08
    åľ¨åĽ½åĨħ
    0.08
    pee
    0.08
     Borders
    0.08
    æ´»å¾Ĺ
    0.08
    Activations Density 0.007%

    No Known Activations