© 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. Qwen3-14B
    5. 20-RESID-BATCHTOPK-65K__L0-80
    7. 16807
    Prev
    Next
    INDEX
    Explanations

    money, prices, and quantities

    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
    缴èĩ³
    -0.23
    æľīæĽ´å¤ļçļĦ
    -0.21
    æıIJä¾ĽæĽ´å¤ļ
    -0.21
    éķ¢
    -0.20
    ÑĢÑıд
    -0.20
    éĨª
    -0.19
    Ñıд
    -0.19
    çĪ±åIJĥ
    -0.19
    äºĨè§£æĽ´å¤ļ
    -0.18
    é²±
    -0.18
    POSITIVE LOGITS
    ä¹°çļĦ
    0.24
    ä¹°äºĨ
    0.24
    å·®çĤ¹
    0.23
    ä¸ĢåıĮ
    0.22
    åĿĩä»·
    0.21
    ç»ĻäºĨæĪij
    0.21
    æīĵäºĨ
    0.21
    ãģłãģ£ãģŁãģ®ãģ§
    0.21
    没æľīæĥ³åĪ°
    0.21
    èİ·å¾ĹäºĨ
    0.21
    Activations Density 0.024%

    No Known Activations