© 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. 10623
    Prev
    Next
    INDEX
    Explanations

    Chinese text

    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
    ellig
    -0.09
    åĨł
    -0.09
    urple
    -0.09
    æľīè¶³å¤ŁçļĦ
    -0.09
    æĻ®éĢļçļĦ
    -0.09
    åıĪ好
    -0.09
    çľ¼è§Ĵ
    -0.08
    Vir
    -0.08
    为åĩĨ
    -0.08
    bab
    -0.08
    POSITIVE LOGITS
    æĺ¯ä¸įåı¯èĥ½
    0.11
    ä¸įæĪIJ
    0.11
    åĬŀåѦ
    0.10
    æĹłç¼ĺ
    0.09
    åīĶ
    0.09
    ãģªãĤĵãģ¦
    0.09
    alem
    0.09
    è¯ķ
    0.09
    çīĩåĪ»
    0.09
    éļ¾å¾Ĺ
    0.09
    Activations Density 0.103%

    No Known Activations