© 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. 13129
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    请åģĩ
    -0.20
    ä¸īåĽ½
    -0.19
    æĿijéķĩ
    -0.19
    ä¼ŀ
    -0.18
    ller
    -0.18
    opr
    -0.17
     СообÑī
    -0.17
    é¡·
    -0.17
    ä»ĸ们éĥ½
    -0.17
     vál
    -0.17
    POSITIVE LOGITS
    .Adam
    0.22
    lays
    0.21
    æĭIJ
    0.19
    æĸ°ä¸Ģè½®
    0.19
    æĸ°çļĦä¸Ģ
    0.18
    جÙħ
    0.18
     past
    0.18
    ular
    0.17
    为代表çļĦ
    0.17
    kus
    0.17
    Activations Density 0.000%

    No Known Activations