© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 36479
    Prev
    Next
    INDEX
    Explanations

    positive online shopping experience

    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
    alytics
    -0.09
    metry
    -0.08
    ients
    -0.08
    æĸ°éĹ»ä¸Ńå¿ĥ
    -0.08
    æł·
    -0.08
    äºijåįĹçľģ
    -0.08
    çŁ³æ²¹åĮĸå·¥
    -0.08
     Gunn
    -0.08
    LineColor
    -0.08
     bestselling
    -0.08
    POSITIVE LOGITS
     experience
    0.27
     experiences
    0.25
    çļĦç»ıåİĨ
    0.24
    ä½ĵéªĮ
    0.24
    ç»ıåİĨ
    0.22
    experience
    0.22
     Experience
    0.21
     ê²½íĹĺ
    0.20
    à¸Ľà¸£à¸°à¸ªà¸ļ
    0.19
     trải
    0.19
    Activations Density 0.114%

    No Known Activations