© 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. 15100
    Prev
    Next
    INDEX
    Explanations

    location and time references

    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
    ä¸ĸä¸Ĭ
    -0.20
    &m
    -0.19
     cry
    -0.19
     curr
    -0.19
     Canton
    -0.19
     existing
    -0.19
    ç´¯
    -0.19
    ä¸įæĿ¥
    -0.18
    çİ°è¡Į
    -0.18
    hab
    -0.18
    POSITIVE LOGITS
    æĸ°çļĦ
    0.32
    ãģ°ãģĭãĤĬ
    0.28
    æĸ°ãģĹãģĦ
    0.25
     اÙĦجدÙĬد
    0.24
    à¹ĥหม
    0.24
    æĸ°
    0.23
    åĪļåĪļ
    0.23
    ä¸įä¹ħ
    0.22
    ä¸įåĨį
    0.21
    ä¸Ģ个æĸ°çļĦ
    0.21
    Activations Density 0.121%

    No Known Activations