© 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. 17297
    Prev
    Next
    INDEX
    Explanations

    power outages and electricity disruptions

    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
     helicopt
    -0.22
     apprentices
    -0.20
    箩
    -0.20
    èĺĸ
    -0.19
    çIJ¢ç£¨
    -0.19
    æł¹æį®èĩªå·±
    -0.18
    åħ¥åѦ
    -0.18
    çļĩå¸Ŀ
    -0.18
    ulos
    -0.18
    åħ¬å¼Ģåıijè¡Į
    -0.18
    POSITIVE LOGITS
    çĶµåĬĽ
    0.27
     electricity
    0.27
    çĶµæºIJ
    0.25
    à¹Ħà¸Ł
    0.25
    ä¸ĢåĪĩ
    0.25
    åģľçĶµ
    0.24
    临æŶ
    0.23
    çĶµ
    0.22
    electric
    0.21
     Electricity
    0.21
    Activations Density 0.028%

    No Known Activations