© 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. 40191
    Prev
    Next
    INDEX
    Explanations

    endothelial or epithelial cells

    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
    åĬ¿å¤´
    -0.10
    æ©ĩ
    -0.10
    oke
    -0.09
    å½
    -0.09
    Ãłng
    -0.09
    è¯¥æł¡
    -0.09
    ä»Ģä¹Īåij¢
    -0.09
    ensely
    -0.09
    ä¸ĭä¸Ģ代
    -0.09
    稳妥
    -0.08
    POSITIVE LOGITS
    å±Ĥ
    0.12
    elial
    0.09
    /interface
    0.09
    layer
    0.09
    人åijĺ
    0.09
    æĮª
    0.09
     layer
    0.09
    以ä¸ĬçļĦ
    0.09
    ä¸Ńè¶ħ
    0.08
    ç»Ĩèĥŀ
    0.08
    Activations Density 0.252%

    No Known Activations