© 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. 11752
    Prev
    Next
    INDEX
    Explanations

    hotel booking and real estate

    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
    æ²¾
    -0.23
     занÑıÑĤ
    -0.20
    åħį
    -0.19
    æ»Ĥ
    -0.19
     Edition
    -0.19
    ä¹Į
    -0.19
    /constants
    -0.18
    åIJ¸åħ¥
    -0.18
     tension
    -0.18
     teng
    -0.18
    POSITIVE LOGITS
    æĹ¶æľº
    0.20
    ERY
    0.20
    stery
    0.20
    Ùĥا
    0.20
     Guerrero
    0.19
     поÑģколÑĮ
    0.19
    KHR
    0.19
    adero
    0.19
    isseur
    0.18
    让æ¶Īè´¹èĢħ
    0.18
    Activations Density 0.001%

    No Known Activations