© 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. 11249
    Prev
    Next
    INDEX
    Explanations

    economic indicators

    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
    ä¸įäºĨ解
    -0.23
     taxp
    -0.23
     danmark
    -0.20
    æĮĩå®ļ
    -0.20
     milfs
    -0.20
     strapon
    -0.20
    ãİĽ
    -0.20
    åĶ®åIJİ
    -0.20
    夸
    -0.18
    .localization
    -0.18
    POSITIVE LOGITS
     overall
    0.33
    çļĦæķ´ä½ĵ
    0.32
    æķ´ä½ĵ
    0.31
    Overall
    0.27
    overall
    0.26
    æĢ»ä½ĵ
    0.26
     levels
    0.21
     index
    0.21
    maf
    0.21
     output
    0.20
    Activations Density 0.090%

    No Known Activations