© 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. 2694
    Prev
    Next
    INDEX
    Explanations

    humor and comedy

    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
    éĢīæĭ
    -0.10
    æģ¶éŃĶ
    -0.09
    èĢģ大
    -0.08
    ynch
    -0.08
    ä¸ĵå¿ĥ
    -0.08
    躲
    -0.08
    奸
    -0.08
     Pest
    -0.08
    Stamp
    -0.08
    ä¼łæŁĵçĹħ
    -0.08
    POSITIVE LOGITS
    å¹½é»ĺ
    0.15
    è¯Ļ
    0.14
    è½»æĿ¾
    0.12
    æIJŀç¬ij
    0.12
    æ´»è·ĥ
    0.11
    ä¸Ģç¬ij
    0.11
     humor
    0.11
    ç¬ijè¯Ŀ
    0.11
    娱ä¹IJ
    0.11
    è°ij
    0.10
    Activations Density 0.035%

    No Known Activations