© 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. 12194
    Prev
    Next
    INDEX
    Explanations

    this time

    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
    è¿Ħä»Ĭ
    -0.21
    ugins
    -0.21
    对æѤ
    -0.20
     nø
    -0.20
    æĬ¹
    -0.19
    绪
    -0.19
    èĩ³æѤ
    -0.19
    æ©IJ
    -0.19
     Slater
    -0.19
    SETS
    -0.19
    POSITIVE LOGITS
    åı«åģļ
    0.24
    æĺ¯ä»¥
    0.23
    主è¦ģæĺ¯
    0.23
    表çݰ为
    0.23
    ä¹Łä¸įä¾ĭå¤ĸ
    0.22
    æĿ¥èĩª
    0.22
    æĺ¯åĽłä¸º
    0.22
    æĺ¯åľ¨
    0.21
     ones
    0.21
    åıĺ为
    0.21
    Activations Density 0.053%

    No Known Activations