© 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. 57745
    Prev
    Next
    INDEX
    Explanations

    wedding and bride related events

    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
     enroll
    -0.09
    åķĸ
    -0.09
    мÑı
    -0.08
    çħĮ
    -0.08
    太åIJİ
    -0.08
    lac
    -0.08
    æľ
    -0.08
    á»ĵn
    -0.08
    شر
    -0.08
    é»İæĺİ
    -0.08
    POSITIVE LOGITS
    å©ļ礼
    0.16
     wedding
    0.13
     brides
    0.12
    wed
    0.12
    å©ļ
    0.12
    ç»ĵå©ļ
    0.11
     weddings
    0.11
     bride
    0.10
    èģĺ
    0.10
     Wedding
    0.10
    Activations Density 0.072%

    No Known Activations