© 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. 16762
    Prev
    Next
    INDEX
    Explanations

    union representatives

    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
    转账
    -0.20
    精彩
    -0.19
    转载请
    -0.19
    antis
    -0.19
    夸大
    -0.18
    æĴŃ
    -0.18
    çIJĨç§ij
    -0.18
    escort
    -0.18
    Friends
    -0.18
    鲨
    -0.18
    POSITIVE LOGITS
    å·¥ä¼ļ
    0.47
     union
    0.38
    ç½¢
    0.36
    工人
    0.35
     unions
    0.35
    åĬ³åĬ¨èĢħ
    0.35
     workers
    0.33
    åijĺå·¥
    0.32
     worker
    0.31
     labor
    0.30
    Activations Density 0.159%

    No Known Activations