© 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. 15107
    Prev
    Next
    INDEX
    Explanations

    shows consequences or risks

    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
    å¹¿æ³ĽåºĶçĶ¨
    -0.22
    å¤ļæł·
    -0.20
    çļĦçľ¼åħī
    -0.20
    ãģ«éĸ¢ãģĹãģ¦
    -0.19
    çIJIJ
    -0.19
    大家éĥ½åľ¨
    -0.18
    çļĦçIJĨ解
    -0.18
    è¯Ŀ说
    -0.18
    ä¹ĭä½Ļ
    -0.18
    æľŁ
    -0.17
    POSITIVE LOGITS
    ç«ĭåĪ»
    0.28
    马ä¸Ĭ
    0.27
    å°±ä¼ļ
    0.25
    ç«ĭåį³
    0.25
     sofort
    0.24
    å¿ħçĦ¶ä¼ļ
    0.24
    å¿ħçĦ¶
    0.23
    ç«ĭ马
    0.23
    å¾Ģå¾Ģ
    0.22
     immediately
    0.21
    Activations Density 0.221%

    No Known Activations