© 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. 9367
    Prev
    Next
    INDEX
    Explanations

    take seriously

    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¡£
    -0.10
    ä¸Ģ身
    -0.09
    大æ´ĭ
    -0.09
    æĢĨ
    -0.09
    èĨı
    -0.09
     Rockefeller
    -0.09
     virtue
    -0.09
    åģļå®Į
    -0.09
    éķ¿å¾ģ
    -0.08
    é»Ŀ
    -0.08
    POSITIVE LOGITS
     seriously
    0.17
    serious
    0.16
     serious
    0.16
    严èĤĥ
    0.16
     seriousness
    0.16
     Serious
    0.15
    è®¤çľŁ
    0.14
     ÑģеÑĢÑĮ
    0.13
     nghiêm
    0.12
    éĩįè§Ĩ
    0.12
    Activations Density 0.039%

    No Known Activations