© 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. 15623
    Prev
    Next
    INDEX
    Explanations

    sulfur emissions and compounds

    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
    åıĸè¯ģ
    -0.21
    馥
    -0.21
    æĮĸæİĺæľº
    -0.20
    æĺ¯æľĢ好çļĦ
    -0.19
    åĿļåĽº
    -0.19
    aupt
    -0.18
    çįŃ
    -0.18
    æĸIJ
    -0.18
    æĭ³
    -0.18
    个人信æģ¯
    -0.18
    POSITIVE LOGITS
    å·¾
    0.27
    纨
    0.21
     pies
    0.21
    ç³Ł
    0.20
     aeros
    0.20
    æľīèī²
    0.20
    åªļ
    0.19
     Rag
    0.19
    é«ĺ空
    0.19
    åĤ¬çĶŁ
    0.19
    Activations Density 0.042%

    No Known Activations