© 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. 56793
    Prev
    Next
    INDEX
    Explanations

    polite requests with please

    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
    æķ£æŃ¥
    -0.09
    iability
    -0.09
    èİ·å¾Ĺ
    -0.08
     stiff
    -0.08
    äºĨä¸Ģåľº
    -0.08
    çĭ®
    -0.08
    çļĦä¸ĢäºĽ
    -0.08
    å·§åIJĪ
    -0.08
    s
    -0.08
    åĿļ强
    -0.08
    POSITIVE LOGITS
    èĥ¸
    0.09
    å¦Ĥå®ŀ
    0.09
    欢è¿İ
    0.09
     tow
    0.09
    achers
    0.09
    ÄŁu
    0.09
    æĪij说
    0.09
    éļıæŶ
    0.09
    å·¥ä¸ļåĮĸ
    0.08
     Pru
    0.08
    Activations Density 0.015%

    No Known Activations