© 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. Qwen3-14B
    5. 20-RESID-BATCHTOPK-65K__L0-80
    7. 15061
    Prev
    Next
    INDEX
    Explanations

    betting and wagering

    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
    æ¼Ķç»İ
    -0.19
    двиг
    -0.19
    alic
    -0.19
    模èĮĥ
    -0.18
    byn
    -0.18
    IClient
    -0.18
    .cuda
    -0.18
    нд
    -0.18
    å·¢
    -0.17
     долж
    -0.17
    POSITIVE LOGITS
    against
    0.23
     bets
    0.21
     against
    0.20
     Zukunft
    0.19
    -taking
    0.19
     rằng
    0.18
    æĬ¼
    0.18
    é¦
    0.18
     Slug
    0.18
    iente
    0.18
    Activations Density 0.006%

    No Known Activations