© 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. 11315
    Prev
    Next
    INDEX
    Explanations

    betting odds and sports

    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
    姥
    -0.20
    è¿Ļ个èģĮä¸ļ
    -0.20
    个人
    -0.19
    ä¹ŁçŁ¥éģĵ
    -0.19
    alth
    -0.19
     catast
    -0.19
    YE
    -0.19
    ä¸įçIJĨ
    -0.19
    hor
    -0.18
    æĥĭ
    -0.18
    POSITIVE LOGITS
    å°º
    0.22
    _unset
    0.19
    踱
    0.19
     اÙĦÙĤدس
    0.19
    upertino
    0.18
    çķª
    0.18
    è·Įçł´
    0.18
    åij½ä¸Ń
    0.18
    /http
    0.18
    áĢĴ
    0.18
    Activations Density 0.003%

    No Known Activations