© 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. 16765
    Prev
    Next
    INDEX
    Explanations

    election campaign finance

    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
    å±¥
    -0.26
    åľ¨å¹¿å·ŀ
    -0.21
    壤
    -0.20
     ÑĢеж
    -0.19
    缺
    -0.19
    å¥ĸåѦéĩij
    -0.19
     зан
    -0.18
     atol
    -0.18
    è´«åĽ°æĪ·
    -0.18
     Radar
    -0.18
    POSITIVE LOGITS
    èĩªçĶ±
    0.19
     liberties
    0.19
    commerce
    0.19
    æ¢Ĺ
    0.19
    idon
    0.19
    .Enable
    0.18
     independent
    0.18
    æģ£
    0.18
     forever
    0.18
    åĭ¿
    0.18
    Activations Density 0.004%

    No Known Activations