© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-8B
    5. 18-RESID-BATCHTOPK-65K__L0-80
    7. 780
    Prev
    Next
    INDEX
    Explanations

    pay and salary differences

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    adamkarvonen/qwen3-8b-saes/saes_Qwen_Qwen3-8B_batch_top_k/resid_post_layer_18
    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
    ankind
    -0.27
     Fate
    -0.26
     unfolding
    -0.26
    (prediction
    -0.24
     Warning
    -0.23
    è·¯åı£
    -0.23
    ä½ľåĵģåĨħ容
    -0.23
    èĤłéģĵ
    -0.23
    èĵį
    -0.22
     Cleanup
    -0.22
    POSITIVE LOGITS
    èĸªéħ¬
    0.59
     salary
    0.56
    èĸªèµĦ
    0.56
     salaries
    0.55
    å·¥èµĦ
    0.51
    salary
    0.50
     wages
    0.49
    å¹´èĸª
    0.48
     wage
    0.47
    Salary
    0.47
    Activations Density 0.039%

    No Known Activations