© 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. 15433
    Prev
    Next
    INDEX
    Explanations

    work and employment

    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
    æĭį
    -0.25
    ยà¸Ńà¸Ķ
    -0.24
    å°ģ
    -0.21
    é«ĺå±Ĥ次
    -0.20
    鸳
    -0.19
    à¹Ĥà¸Ķ
    -0.19
    Coach
    -0.19
    è¿ĩåħ³
    -0.19
     Toll
    -0.18
    大åĴĸ
    -0.18
    POSITIVE LOGITS
    åĬ³åĬ¨
    0.45
    åĬ³åĬ¨èĢħ
    0.41
     labor
    0.40
    åĬ³åĬ¨åĬĽ
    0.37
     labour
    0.35
     jobs
    0.35
    å°±ä¸ļ
    0.34
    å·¥ä½ľå²Ĺä½į
    0.34
    åĭ¤åĬ³
    0.34
    æīĵå·¥
    0.34
    Activations Density 0.203%

    No Known Activations