© 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. 16832
    Prev
    Next
    INDEX
    Explanations

    by using this

    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
    æĺ¯ä¸ª
    -0.24
    åĢ¼å¾Ĺåħ³æ³¨
    -0.22
    æĿ¡ä»¶ä¸ĭ
    -0.21
    æĺ¯ä¸Ģ
    -0.20
    èĩªä»İ
    -0.20
    inct
    -0.20
    åĽłä¸ºåľ¨
    -0.19
    å¦Ĥæŀľæľī
    -0.19
    æį¢äºĨ
    -0.19
    æ³ķå®ļ
    -0.19
    POSITIVE LOGITS
    è¿Ļç§įæĸ¹å¼ı
    0.23
    åı¯ä»¥è®©
    0.22
    ìį¨
    0.21
    æĤ¨åIJĮæĦı
    0.21
    åı¯ä»¥ä½¿
    0.20
     means
    0.20
    æĪijåı¯ä»¥
    0.19
     podemos
    0.19
    gain
    0.18
    rd
    0.18
    Activations Density 0.072%

    No Known Activations