© 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. 14193
    Prev
    Next
    INDEX
    Explanations

    outsourcing manufacturing locations

    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
    ç²¾ç¥ŀæĸĩæĺİ
    -0.20
    åIJĦçķĮ
    -0.19
    éªł
    -0.19
    æľīæķĪåľ°
    -0.19
    窦
    -0.19
    æ¶Īéĺ²å®īåħ¨
    -0.19
    åģ¥åº·çļĦ
    -0.19
     interceptor
    -0.19
     Dead
    -0.18
    èŀįåĪĽ
    -0.18
    POSITIVE LOGITS
     outsourcing
    0.24
    å¤ĸåĮħ
    0.23
    ä¸ŃåĽ½åĪ¶éĢł
    0.22
    çĶŁäº§çº¿
    0.22
    éĻįä½İæĪIJæľ¬
    0.21
     manufacturing
    0.21
     locations
    0.21
    çĶŁäº§
    0.21
    大éĻĨ
    0.21
     overseas
    0.21
    Activations Density 0.046%

    No Known Activations