© 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. 16622
    Prev
    Next
    INDEX
    Explanations

    sports actions and results

    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
    edition
    -0.20
     Clair
    -0.20
    anian
    -0.20
    sworth
    -0.20
    feit
    -0.19
    atitude
    -0.19
    åįĩèµ·
    -0.18
    cedes
    -0.18
    糧
    -0.18
    endale
    -0.18
    POSITIVE LOGITS
    tee
    0.21
     ÑģлÑĥÑĩай
    0.21
    糧
    0.20
    åĬ¨çĶŁæĪIJ
    0.20
    æĭ¦æĪª
    0.19
    è¿Ļæł·ä¸Ģ
    0.19
    路人
    0.19
    è¹Ń
    0.18
     contempor
    0.18
    kö
    0.18
    Activations Density 0.004%

    No Known Activations