© 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. 14669
    Prev
    Next
    INDEX
    Explanations

    construction jobs and work crews

    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¯Ħ
    -0.20
    æķ¢äºİ
    -0.19
    交æĺĵæīĢ
    -0.18
     iceberg
    -0.18
    æ¡Įä¸Ĭ
    -0.18
    æijĦ
    -0.18
     pinned
    -0.18
     Tu
    -0.18
    boarding
    -0.17
    代è¨Ģ
    -0.17
    POSITIVE LOGITS
    æĸ½å·¥
    0.43
     construction
    0.38
    干活
    0.37
    construction
    0.35
    Construction
    0.35
     Construction
    0.35
     ìŀijìĹħ
    0.33
    ä½ľä¸ļ
    0.33
    åĬ³åĬ¨
    0.30
    建è¨Ń
    0.30
    Activations Density 0.160%

    No Known Activations