© 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. 6089
    Prev
    Next
    INDEX
    Explanations

    caries and cavities

    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
    .ba
    -0.10
    çıł
    -0.09
    Rad
    -0.09
    被æįķ
    -0.09
    åģĩ
    -0.08
     abre
    -0.08
    éĹº
    -0.08
    姹
    -0.08
    åįİ缼
    -0.08
    离éĢĢä¼ij
    -0.08
    POSITIVE LOGITS
    èĽĢ
    0.14
    é¾ĭ
    0.13
     ÑģаÑħ
    0.09
    åĿIJ
    0.09
     cav
    0.09
     cavity
    0.09
    æ½ľ
    0.09
    bib
    0.08
    ä½ı
    0.08
    à¸ĵะ
    0.08
    Activations Density 0.173%

    No Known Activations