© 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. 1986
    Prev
    Next
    INDEX
    Explanations

    clubs and societies

    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
    yi
    -0.10
    bright
    -0.09
    emann
    -0.09
    éºĴ
    -0.08
    éķ¶
    -0.08
    æķ¬ä¸ļ
    -0.08
    èĭ´
    -0.08
    æķĻåѦ
    -0.08
    amas
    -0.08
    hem
    -0.08
    POSITIVE LOGITS
    ç¤¾åĽ¢
    0.14
    æ´»åĬ¨
    0.10
    毯
    0.10
    åħ¨æł¡
    0.10
    extr
    0.10
    çļĦçĥŃæĥħ
    0.10
     rtl
    0.09
    åį°ç«ł
    0.09
    å¯Ŀ室
    0.09
    主åĬŀ
    0.09
    Activations Density 0.064%

    No Known Activations