© 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. 426
    Prev
    Next
    INDEX
    Explanations

    taxation and income

    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
    åĵ¨
    -0.24
     repertoire
    -0.24
    æݨä»ĭ
    -0.23
     reputation
    -0.23
    presence
    -0.23
     impress
    -0.23
    æĦ
    -0.23
     presence
    -0.23
    åĩºåĵģ
    -0.23
    æݨèįIJ
    -0.23
    POSITIVE LOGITS
     income
    0.32
    ä¸ĩæĪ·
    0.30
    æīĢå¾Ĺç¨İ
    0.30
     homeowners
    0.29
    纳ç¨İ人
    0.28
     incomes
    0.28
     homeowner
    0.28
     taxable
    0.28
    大æĪ·
    0.28
    -income
    0.27
    Activations Density 0.024%

    No Known Activations