© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-14B
    5. 20-RESID-BATCHTOPK-65K__L0-80
    7. 17099
    Prev
    Next
    INDEX
    Explanations

    &T, Verizon, Telstra"}, Wireless, service

    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
    Negative Logits
    微信群
    -0.21
    åĭ¤åĬ³
    -0.21
    çŃĶåį·
    -0.19
    views
    -0.19
    ä¸Ńåħ³
    -0.18
    æıª
    -0.18
    çĶµç«ŀ
    -0.18
     Marina
    -0.18
    å®´
    -0.18
    讼
    -0.17
    POSITIVE LOGITS
    éŀį
    0.21
    第ä¸Ģ家
    0.21
    çīĪ
    0.21
    åĬłæĮģ
    0.20
    订è´Ń
    0.20
    æݨåĩº
    0.20
    çīĪæľ¬
    0.20
    é¦ĸåıij
    0.20
     offerings
    0.20
    RELEASE
    0.20
    Activations Density 0.011%

    No Known Activations