© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-8B
    5. 18-RESID-BATCHTOPK-65K__L0-80
    7. 374
    Prev
    Next
    INDEX
    Explanations

    days of the week and dates

    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
    è¿Ļæĸ¹éĿ¢
    -0.24
    ÑĢай
    -0.23
    hoa
    -0.23
    奢
    -0.22
    awi
    -0.21
    lux
    -0.21
    çļİ
    -0.21
    adopt
    -0.21
    amp
    -0.21
    ry
    -0.21
    POSITIVE LOGITS
     afternoon
    0.30
    ä¸ĬåįĪ
    0.28
     eve
    0.28
     morning
    0.28
    åĩĮæĻ¨
    0.26
    æ¸ħæĻ¨
    0.25
     touchdown
    0.25
    æĹ©æĻ¨
    0.25
    第äºĮ天
    0.25
     Eve
    0.24
    Activations Density 0.017%

    No Known Activations