© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-14B
    5. 20-RESID-BATCHTOPK-65K__L0-80
    7. 12203
    Prev
    Next
    INDEX
    Explanations

    celebrations and life events

    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
     hẹn
    -0.22
    æī¾ä¸ª
    -0.21
     Boh
    -0.21
    ç«ŀéĢī
    -0.21
    uffed
    -0.19
    æīĵåIJ¬
    -0.19
    æµĵåİļ
    -0.18
    ÑĪение
    -0.18
    让æĤ¨
    -0.18
    åIJį人
    -0.18
    POSITIVE LOGITS
    第äºĮ天
    0.23
    éĤ£å¤©
    0.19
    æĪijåİ»
    0.18
    éĤ»å±ħ
    0.18
     tầ
    0.18
    osas
    0.18
    次
    0.18
     عÙĦÙĬÙĨا
    0.18
    ç»ı纬
    0.18
     UIL
    0.17
    Activations Density 0.019%

    No Known Activations