© 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. 49383
    Prev
    Next
    INDEX
    Explanations

    humor, joke, laugh, funny

    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
    ç²¾
    -0.09
    缴éĢļ车
    -0.08
    ç´¯
    -0.08
    åĬłæ²¹
    -0.08
    church
    -0.08
    .pivot
    -0.08
    olly
    -0.08
    Church
    -0.08
    åIJĥçļĦ
    -0.08
    è¶
    -0.08
    POSITIVE LOGITS
    rud
    0.09
    鸫
    0.09
    æĤ¬
    0.09
    äºī缸
    0.08
    å»ĵ
    0.08
    èµı
    0.08
     khả
    0.08
    [".
    0.08
    enance
    0.08
    zahl
    0.08
    Activations Density 0.014%

    No Known Activations