© 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. 13488
    Prev
    Next
    INDEX
    Explanations

    socially relevant issues and messages

    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
     nghè
    -0.27
    åij¨è½¬
    -0.24
    ç»ıèIJ¥èĮĥåĽ´
    -0.23
    ç»ıèIJ¥èĢħ
    -0.22
    åľ¨çݩ家ä¸Ń
    -0.21
    åįķèģĮä¸ļ
    -0.21
    çݩ家æľĭåıĭ
    -0.20
    ä¸ĭ游
    -0.20
    æľįåĬ¡ä½ĵç³»
    -0.20
    çĵ»
    -0.20
    POSITIVE LOGITS
    çİ°å®ŀ
    0.28
     themes
    0.27
    å¯ĵ
    0.27
     alleg
    0.24
    ä»·åĢ¼è§Ĥ
    0.23
     depiction
    0.22
    åıį
    0.21
    é¢ĺæĿIJ
    0.21
    og
    0.21
    æݢ讨
    0.21
    Activations Density 0.088%

    No Known Activations