© 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. Qwen3-14B
    5. 20-RESID-BATCHTOPK-65K__L0-80
    7. 12501
    Prev
    Next
    INDEX
    Explanations

    Crusades, Antioxidant, Magnesium, Order

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    adamkarvonen/qwen3-14b-saes/saes_Qwen_Qwen3-14B_batch_top_k/resid_post_layer_20
    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
    å°¾
    -0.21
    åľ¨åŃ¦æł¡
    -0.20
    辨
    -0.20
    宪
    -0.20
    åħ¬ç«ł
    -0.20
    çĪ±ä½ł
    -0.19
    åĮĻ
    -0.19
    ä¹īä¹Į
    -0.19
    åľ¨æł¡
    -0.18
    串
    -0.18
    POSITIVE LOGITS
    ä½ľæĪĺ
    0.23
    æĪĺåľºä¸Ĭ
    0.23
    æ§İ
    0.22
     wars
    0.20
    åľ°ä¸Ńæµ·
    0.20
     relic
    0.19
    è¸ı
    0.19
    建éĢł
    0.19
    éķ¿åŁİ
    0.19
    -build
    0.19
    Activations Density 0.017%

    No Known Activations