© 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. 18675
    Prev
    Next
    INDEX
    Explanations

    quoted speech marks

    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
    å·¥ä¸ļåĮĸ
    -0.11
    äºĨæĪijçļĦ
    -0.11
    å°±è¿Ļä¹Ī
    -0.10
    äºĨåIJĹ
    -0.09
    ä¸Ģ缴éĥ½æĺ¯
    -0.09
    çļĦ第ä¸Ģ个
    -0.09
    cer
    -0.09
    ï¸
    -0.09
    åľ¨éĩĮéĿ¢
    -0.09
    è¿Ļä¹Īåģļ
    -0.09
    POSITIVE LOGITS
    ãĢĿ
    0.09
     “
    0.09
     ÙħØ´ÙĬرا
    0.08
    ãĢĮ
    0.08
    以为
    0.08
    åIJĮæł·æĺ¯
    0.08
    ãĢģ“
    0.08
    efined
    0.08
    encial
    0.08
    ï¼ļ“
    0.07
    Activations Density 0.041%

    No Known Activations