© 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. 58562
    Prev
    Next
    INDEX
    Explanations

    actions like get, find, compare

    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
    åĽ¾ä¸º
    -0.09
    lef
    -0.09
    unsch
    -0.09
    ä¸įè¦ģåĨį
    -0.08
    éĿŀ常好
    -0.08
    stakes
    -0.08
    ãĤ¹ãĥĿ
    -0.08
    è¦ģåľ¨
    -0.08
     inds
    -0.08
    åľ»
    -0.08
    POSITIVE LOGITS
    ä¸Ģ个人
    0.09
    èĢ¨
    0.09
     Jelly
    0.09
    åįķçĭ¬
    0.09
    æŃ¥
    0.09
    çļĦä¸ĢéĿ¢
    0.09
    硬
    0.09
    wap
    0.09
    æĪIJ为ä¸Ģ个
    0.09
    çľĭåĩº
    0.09
    Activations Density 0.045%

    No Known Activations