© 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. 12127
    Prev
    Next
    INDEX
    Explanations

    not preclusion

    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¿ĻæŶåĢĻ
    -0.28
    è¿Ļ个è¯į
    -0.24
     ÙĩØ°Ùĩ
    -0.23
     nÃły
    -0.23
    è¿Ļä¹Ł
    -0.23
    è¿Ļ个æŶåĢĻ
    -0.23
    åľ¨è¿Ļ个
    -0.23
     ÑįÑĤом
    -0.23
    äºİæѤ
    -0.22
    åľ¨è¿Ļæĸ¹éĿ¢
    -0.22
    POSITIVE LOGITS
    åıijçĶŁåľ¨
    0.27
     happening
    0.26
    ä¸įæĺ¯ä¸Ģ个
    0.24
    æĺ¯ä¸Ģ件
    0.22
    æĪijçļĦ
    0.22
    æĹłçĸijæĺ¯
    0.22
    çĶ·åŃIJ
    0.21
    æĺ¯ä¸Ģ项
    0.21
    aget
    0.21
    æĹłçĸij
    0.21
    Activations Density 0.378%

    No Known Activations