© 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. 10834
    Prev
    Next
    INDEX
    Explanations

    weightlifting and exercise

    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
    ç¼ľ
    -0.22
    éļĻ
    -0.22
    æ¯ĹéĤ»
    -0.21
    æ·Į
    -0.20
     поб
    -0.19
    æ»ļçIJĥ
    -0.19
    é¬ĵ
    -0.19
    è¿Ĥ
    -0.19
    è£Ļ
    -0.19
    æĨİ
    -0.19
    POSITIVE LOGITS
    éĩįéĩı
    0.25
    æŀģéĻIJ
    0.24
    weights
    0.23
    weight
    0.23
     weight
    0.22
    åħ¬æĸ¤
    0.22
    æĪIJ绩
    0.21
    è´Łèį·
    0.21
     lifting
    0.20
     weights
    0.20
    Activations Density 0.017%

    No Known Activations