© 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. 16384
    Prev
    Next
    INDEX
    Explanations

    yoga and related poses

    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
    æºħ
    -0.22
    æĮŀ
    -0.22
    ChildIndex
    -0.21
    åŃº
    -0.21
    åIJ»
    -0.21
    èħIJèļĢ
    -0.21
    éĽĦ
    -0.20
    elda
    -0.20
    åķĨæľº
    -0.20
    棹
    -0.20
    POSITIVE LOGITS
     yoga
    0.40
    çijľä¼½
    0.39
     Yoga
    0.32
    ä¿®è¡Į
    0.28
     yog
    0.23
     meditation
    0.23
    изм
    0.23
    èĢģåŃIJ
    0.22
    ðŁ§ĺ
    0.21
    åĥ§
    0.21
    Activations Density 0.024%

    No Known Activations