© 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. 58075
    Prev
    Next
    INDEX
    Explanations

    one of those

    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
    笼
    -0.10
    chio
    -0.09
    主èIJ¥ä¸ļ
    -0.09
    æķ¦çħĮ
    -0.09
    æ¯ıä¸Ģ个人
    -0.09
    çļĦä¸ĢéĿ¢
    -0.09
    %%%%
    -0.08
    æµħ
    -0.08
    scanner
    -0.08
    оваÑı
    -0.08
    POSITIVE LOGITS
    otec
    0.09
    ething
    0.09
    ä¼ŀ
    0.09
    ãģĵãģ¨ãģ§ãģĻ
    0.09
     occasions
    0.08
    åĪ¤
    0.08
    ä½İä½į
    0.08
    arer
    0.08
     Gem
    0.08
    壹
    0.08
    Activations Density 0.022%

    No Known Activations