© 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. 11640
    Prev
    Next
    INDEX
    Explanations

    austerity, cuts, economic adjustment

    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
    -0.23
     giác
    -0.22
    æĹłçº¿çĶµ
    -0.21
    æ¶Īè´¹åįĩ级
    -0.21
    åºĶçĶ¨åľºæĻ¯
    -0.21
    ä¸ĭä¸Ģ代
    -0.20
    éģ¿åŃķ
    -0.20
    æľ¨åľ°æĿ¿
    -0.20
    åıijè¨Ģ人
    -0.20
    壤
    -0.19
    POSITIVE LOGITS
     dereg
    0.26
     neoliberal
    0.25
     usher
    0.24
     austerity
    0.22
     executive
    0.20
    icts
    0.20
     shrink
    0.20
     bankrupt
    0.20
    -government
    0.20
     Ske
    0.20
    Activations Density 0.028%

    No Known Activations