© 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. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 48010
    Prev
    Next
    INDEX
    Explanations

    skilled workforce and training

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    adamkarvonen/qwen3-32b-saes/saes_Qwen_Qwen3-32B_batch_top_k/resid_post_layer_32
    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
     Surv
    -0.10
    -blog
    -0.10
    arium
    -0.09
    æ§Ĭ
    -0.09
    èĢģ人家
    -0.08
    æĻ®
    -0.08
    OLLOW
    -0.08
    俱ä¹IJéĥ¨
    -0.08
    æľīæĿ¡ä»¶çļĦ
    -0.08
     activity
    -0.08
    POSITIVE LOGITS
    人æīį
    0.16
    é«ĺç´łè´¨
    0.16
     skilled
    0.15
    工人
    0.14
    çĨŁç»ĥ
    0.13
    æĬĢèĥ½åŁ¹è®Ń
    0.13
    人æīįåŁ¹åħ»
    0.13
    æĬĢèĥ½
    0.13
     workforce
    0.12
    人åijĺ
    0.12
    Activations Density 0.054%

    No Known Activations