© 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. 24268
    Prev
    Next
    INDEX
    Explanations

    treatments for ailments

    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
    æįħ
    -0.11
    åģĪ
    -0.10
    æİ¥åĬĽ
    -0.10
    æݥ管
    -0.09
    æŁ¿
    -0.09
    ä¸įå®ļ
    -0.09
    è¯ĺ
    -0.09
    éĻª
    -0.09
    bes
    -0.09
    强åĬĽ
    -0.09
    POSITIVE LOGITS
     treat
    0.10
     Treat
    0.10
    -treated
    0.10
    Ĥ¤
    0.09
     behand
    0.09
    usher
    0.09
     tratt
    0.09
    æĭĵ
    0.09
    شا
    0.09
    akis
    0.08
    Activations Density 0.144%

    No Known Activations