© 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. Qwen3-8B
    5. 18-RESID-BATCHTOPK-65K__L0-80
    7. 2201
    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/qwen3-8b-saes/saes_Qwen_Qwen3-8B_batch_top_k/resid_post_layer_18
    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
     drive
    -0.23
     ide
    -0.23
    illions
    -0.23
     tors
    -0.23
     mate
    -0.23
    pager
    -0.22
    çĥĬ
    -0.22
     outdoors
    -0.22
     ideology
    -0.22
    mere
    -0.22
    POSITIVE LOGITS
    å¹½é»ĺ
    0.46
     humour
    0.36
     humor
    0.35
    讽åĪº
    0.31
     humorous
    0.29
    è¯Ļ
    0.29
     comedy
    0.25
    活泼
    0.24
    è°ĥä¾ĥ
    0.24
    åĸľåī§
    0.23
    Activations Density 0.060%

    No Known Activations