© 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. 17057
    Prev
    Next
    INDEX
    Explanations

    economic development positions and organizations

    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
    ä¸įå¼Ģ
    -0.21
    åĽ½éģĵ
    -0.21
    äºī
    -0.20
    ç²¾è£ħ
    -0.20
    åĨľä¸ļç§ijæĬĢ
    -0.19
    åįł
    -0.19
     ÑĥнивеÑĢÑģ
    -0.19
    åįłæį®äºĨ
    -0.18
    éĩįè¦ģæĦıä¹ī
    -0.18
    åħ¬åħ±èµĦæºIJ
    -0.18
    POSITIVE LOGITS
    廨
    0.21
    åģľä¸ĭæĿ¥
    0.19
    ITT
    0.18
    éķĢ
    0.18
    need
    0.18
    Disp
    0.18
    æµı
    0.17
    /accounts
    0.17
    åıī
    0.17
    club
    0.17
    Activations Density 0.001%

    No Known Activations