© 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. 11956
    Prev
    Next
    INDEX
    Explanations

    lifestyle and consumption habits

    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
     bigot
    -0.22
    ç»Ĵ
    -0.22
    çĭ¡
    -0.22
    auty
    -0.21
    ä¼ŀ
    -0.21
     ÑģпÑĢав
    -0.20
    æľºåĪ¶
    -0.20
    çļĦå¿ĥæĥħ
    -0.20
     nameof
    -0.20
    ä¸ĭå·´
    -0.20
    POSITIVE LOGITS
     lifestyle
    0.26
    éħĹ
    0.24
    æĹºçĽĽ
    0.23
    ifestyle
    0.22
     habits
    0.22
     nightlife
    0.22
    .consume
    0.21
     consumption
    0.20
    azz
    0.20
    .dateFormat
    0.20
    Activations Density 0.029%

    No Known Activations