© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 7893
    Prev
    Next
    INDEX
    Explanations

    time and clock settings

    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
    ä½İä¿Ŀ
    -0.11
     Merkel
    -0.10
    çľĭå¾Ĺ
    -0.09
    æŀ·
    -0.09
    ismo
    -0.09
     revolutions
    -0.09
    åħ³å¿ĥ
    -0.09
    åģķ
    -0.08
    hausen
    -0.08
    åĶ®ä»·
    -0.08
    POSITIVE LOGITS
    åĮ¡
    0.10
    ä¹ĥ
    0.09
    åģıå·®
    0.09
    еÑģÑĮ
    0.09
    çĶµèĦij
    0.08
    ä¿®æŃ£
    0.08
    çłĶ讨ä¼ļ
    0.08
    奥è¿IJ
    0.08
     Sag
    0.08
    .imshow
    0.08
    Activations Density 0.060%

    No Known Activations