© 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. 26592
    Prev
    Next
    INDEX
    Explanations

    chinese cultural or linguistic elements

    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
    åŁĥåıĬ
    -0.11
    å¸ĥé²ģ
    -0.09
    èĤ
    -0.09
    éŀŃ
    -0.09
    çŁ³åĮĸ
    -0.09
     Fem
    -0.09
    Úĺ
    -0.09
    æĥħæĬ¥
    -0.09
    ittal
    -0.09
     bande
    -0.08
    POSITIVE LOGITS
    æĸĩåĮĸèīºæľ¯
    0.10
    éĿ¢èī²
    0.09
    é¥Ń
    0.09
    ä¹ĭ乡
    0.08
    çĶ»åį·
    0.08
    礼仪
    0.08
    æijŀ
    0.08
    æĸĩåĮĸåºķèķ´
    0.08
     DIM
    0.08
    äºĶè¡Į
    0.08
    Activations Density 0.083%

    No Known Activations