© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 61415
    Prev
    Next
    INDEX
    Explanations

    breast-feeding and lactation

    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
    Not in Any Lists

    No Comments

    Negative Logits
    åı¯è§Ĩ
    -0.09
    ÑĥÑĩ
    -0.09
    вид
    -0.08
    æĢĢçĿĢ
    -0.08
     Eu
    -0.08
    ä¸Ģæĺ¯
    -0.08
    å¾Īå°ı
    -0.08
    æľīæķĪçļĦ
    -0.08
    æĺ¾çĦ¶æĺ¯
    -0.08
    DIC
    -0.08
    POSITIVE LOGITS
    åĭĸ
    0.10
    Toggle
    0.09
    æľ´ç´ł
    0.09
    绵
    0.09
     thá»ıa
    0.09
    _devices
    0.09
    uke
    0.08
    åºĸ
    0.08
     Huff
    0.08
    éĢ»è¾ij
    0.08
    Activations Density 0.016%

    No Known Activations