© 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. 37330
    Prev
    Next
    INDEX
    Explanations

    joking and humor

    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
    Boom
    -0.09
    åIJ¸åħ¥
    -0.09
    urger
    -0.08
    丧
    -0.08
    èĬ±çº¹
    -0.08
    èľ·
    -0.08
     Dem
    -0.08
    bis
    -0.08
    å§ĭ
    -0.08
    izzle
    -0.07
    POSITIVE LOGITS
    å¹½é»ĺ
    0.23
    è°ĥä¾ĥ
    0.22
    çİ©ç¬ij
    0.20
    ä¸Ģç¬ij
    0.19
    è¯Ļ
    0.18
    ç¬ij
    0.17
    å¼Ģçİ©ç¬ij
    0.17
    ç¬ijçĿĢ
    0.17
     humor
    0.16
    ç¬ijçĿĢ说
    0.16
    Activations Density 0.047%

    No Known Activations