© 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. 32952
    Prev
    Next
    INDEX
    Explanations

    platform or device

    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
    è¿Ļä¸Ģ
    -0.08
    ä¸Ģ个å°ı
    -0.08
    ä¸Ģå®ļçļĦ
    -0.07
    çļĦä¸ĢäºĽ
    -0.07
    æľīçļĦ
    -0.07
    ç¬ĥ
    -0.07
    çļĦãģª
    -0.07
    çİ°éĺ¶æ®µ
    -0.07
     a
    -0.07
     SENT
    -0.07
    POSITIVE LOGITS
    æģ¢
    0.10
    nut
    0.10
    éļĪ
    0.09
    )arg
    0.09
    æĬĢæľ¯çłĶåıij
    0.09
    å·§åIJĪ
    0.09
    è·¨è¶Ĭå¼ı
    0.09
    áĥij
    0.09
    æĻģ
    0.09
    å·¥ç¨ĭé¡¹çĽ®
    0.09
    Activations Density 0.240%

    No Known Activations