© 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. 17087
    Prev
    Next
    INDEX
    Explanations

    World War II

    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
    åľ¨çİ°åľº
    -0.24
    ä¸įåİ»
    -0.22
     sẵ
    -0.19
     апп
    -0.18
    åĮĻ
    -0.18
    å¤Ħ
    -0.18
     nghè
    -0.18
    åĵį
    -0.18
    itr
    -0.17
    åŁİåĮº
    -0.17
    POSITIVE LOGITS
    -era
    0.29
    ç»ĵæĿŁåIJİ
    0.28
    æĪĺäºī
    0.28
    æĹ¶æľŁ
    0.27
    è¿Ļåľº
    0.27
    æĹ¶æľŁçļĦ
    0.27
    æľŁéĹ´
    0.27
    æľŁéĸĵ
    0.24
    å±ĢåĬ¿
    0.23
     period
    0.23
    Activations Density 0.045%

    No Known Activations