© 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. 10701
    Prev
    Next
    INDEX
    Explanations

    said attorney

    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
    æĬĬèĩªå·±çļĦ
    -0.21
    å§Ĭ妹
    -0.20
    =top
    -0.19
     Garden
    -0.19
     garden
    -0.19
     topo
    -0.19
    åŀ¦
    -0.19
     yuk
    -0.18
     Douglas
    -0.18
    åıijçİ°èĩªå·±
    -0.18
    POSITIVE LOGITS
    没æľīå¿ħè¦ģ
    0.23
     bÃło
    0.21
    çŃĸçķ¥
    0.21
    称
    0.21
    éĢĴ交
    0.20
    ä¸īæĸ¹
    0.19
     auss
    0.19
    称ä¹ĭ
    0.19
    éĻª
    0.19
    åĿļ
    0.19
    Activations Density 0.027%

    No Known Activations