© 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. 16882
    Prev
    Next
    INDEX
    Explanations

    jobs and employment opportunities

    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
    æĹłæķĮ
    -0.19
    succ
    -0.19
    éĻªä½ł
    -0.19
    å¥łåŁº
    -0.19
    çľł
    -0.19
    æĹħ游å±Ģ
    -0.19
     retreat
    -0.19
    å¯Ħ
    -0.18
    缼è¡Į
    -0.18
    ä½łè¦ģ
    -0.18
    POSITIVE LOGITS
    å°±ä¸ļå²Ĺä½į
    0.32
    æľ¬åľ°
    0.30
     jobs
    0.30
    å°±ä¸ļ
    0.29
     local
    0.29
     employment
    0.29
    带åĬ¨
    0.28
    å½ĵåľ°
    0.26
    local
    0.25
     lokal
    0.24
    Activations Density 0.076%

    No Known Activations