© 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. 14094
    Prev
    Next
    INDEX
    Explanations

    Portuguese and Spanish words

    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
    éļ¶å±ŀäºİ
    -0.21
    @(
    -0.19
    æĭĺ
    -0.19
    纲
    -0.19
    缸éĤ»
    -0.18
    âĢij
    -0.18
    atee
    -0.18
    antly
    -0.18
    FirstChild
    -0.17
    è¿ŀäºij
    -0.17
    POSITIVE LOGITS
    æĦıæĢĿæĺ¯
    0.33
     (“
    0.30
     ("
    0.29
     literally
    0.24
     ('
    0.23
    çļĦæĦıæĢĿ
    0.23
    ä¹Łå°±æĺ¯è¯´
    0.21
     meaning
    0.21
     means
    0.21
    ä¿Ĺ称
    0.21
    Activations Density 0.400%

    No Known Activations