© 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. 12014
    Prev
    Next
    INDEX
    Explanations

    company names ending with Corporation/Group/Foods/Company

    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
    uggy
    -0.19
    вид
    -0.19
    .travel
    -0.18
    ä¸Ģåij³
    -0.18
    bill
    -0.17
    åĪ©çİĩ
    -0.17
    å¾Ĥ
    -0.17
    åĩłä½ķ
    -0.17
    dued
    -0.17
    ihan
    -0.17
    POSITIVE LOGITS
    ViewItem
    0.21
    ä¸Ģ头
    0.21
    opoly
    0.19
    æĢ»åħ¬åı¸
    0.18
     campaigners
    0.18
    ä½ľçī©
    0.18
     Agu
    0.18
    IgnoreCase
    0.17
    ae
    0.17
    æľ¬ç«Ļ
    0.17
    Activations Density 0.003%

    No Known Activations