© 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. Qwen3-8B
    5. 18-RESID-BATCHTOPK-65K__L0-80
    7. 2057
    Prev
    Next
    INDEX
    Explanations

    luxury goods / fine items

    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
     redd
    -0.24
    sWith
    -0.24
    MRI
    -0.23
    æŀ¯
    -0.23
    åĵĮ
    -0.22
     Burning
    -0.22
    派驻
    -0.22
    oley
    -0.22
     Morm
    -0.22
    ç£ģ
    -0.22
    POSITIVE LOGITS
     luxury
    0.27
    享
    0.25
    lux
    0.24
    奢ä¾Īåĵģ
    0.23
    åĽ½åĬ¡
    0.23
    grand
    0.23
     deluxe
    0.23
    åĵģ
    0.23
    æ¡Ī件
    0.23
    æīĭæĮģ
    0.23
    Activations Density 0.015%

    No Known Activations