© 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. 279
    Prev
    Next
    INDEX
    Explanations

    moon, surface, Earth, lunar

    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
    Ø£Ùĩد
    -0.25
    неÑĨ
    -0.24
    AllWindows
    -0.24
     nw
    -0.23
     Fitness
    -0.23
    æ¢ı
    -0.23
    平常
    -0.22
    æł¹
    -0.22
    åIJijä¸Ĭ
    -0.22
     Imported
    -0.22
    POSITIVE LOGITS
     asteroid
    0.34
    æİ¢æµĭ
    0.33
    åįĹæŀģ
    0.31
    åľ°çIJĥä¸Ĭ
    0.31
     Earth
    0.30
     lunar
    0.30
    NASA
    0.29
     NASA
    0.29
    éģĹåĿĢ
    0.29
     surface
    0.29
    Activations Density 0.020%

    No Known Activations