© 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. 15608
    Prev
    Next
    INDEX
    Explanations

    dates and numbers

    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
    è¿ĻæĿ¡
    -0.20
    èī¯
    -0.20
    alo
    -0.19
    ä¸įçķĻ
    -0.19
     slee
    -0.18
    æĬļ
    -0.18
    åı¯æł¹æį®
    -0.18
    .sqlite
    -0.18
    ä¸İåħ¶
    -0.18
    ï¸ı
    -0.18
    POSITIVE LOGITS
    pink
    0.20
     dạy
    0.20
    (:,:,
    0.19
    rán
    0.19
    à¦ĩ
    0.19
    PropTypes
    0.18
    /animate
    0.18
    è·ŁæĪij说
    0.18
     evils
    0.18
    è´ŁåĢº
    0.17
    Activations Density 0.011%

    No Known Activations