© 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. 27549
    Prev
    Next
    INDEX
    Explanations

    humor and laughter

    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
    æłĹ
    -0.09
    ä¸ĵåįĸåºĹ
    -0.09
    äºĨ个
    -0.09
    éĤ£ç§į
    -0.08
    涨
    -0.08
    çļİ
    -0.08
    åĶ®
    -0.08
    襻
    -0.08
     loose
    -0.08
    å½¹
    -0.08
    POSITIVE LOGITS
    çİ©ç¬ij
    0.11
    å¹½é»ĺ
    0.10
    å¼ĢæľĹ
    0.10
    è¾ĵ
    0.09
    活泼
    0.09
    å¼Ģçİ©ç¬ij
    0.09
    anke
    0.09
     ÑģиÑĤÑĥаÑĨиÑı
    0.09
    éĺ²ç©º
    0.09
    综èīº
    0.09
    Activations Density 0.013%

    No Known Activations