© 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. 14366
    Prev
    Next
    INDEX
    Explanations

    outlet locations

    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
    åı¸
    -0.21
    转æĬĺ
    -0.21
    æł¸å¿ĥ
    -0.19
    ovi
    -0.18
    åIJ¹
    -0.18
     Bret
    -0.17
    $core
    -0.17
    .getBytes
    -0.17
     Sher
    -0.17
     wasted
    -0.17
    POSITIVE LOGITS
    -only
    0.22
    鸢
    0.19
    аÑĢам
    0.19
    ucher
    0.19
    è¿Ļç§įæĸ¹å¼ı
    0.19
    æĭĽå¾ħ
    0.19
    客æĪ·çļĦ
    0.19
    客æĪ·æıIJä¾Ľ
    0.18
    çł¾
    0.18
     Burgess
    0.18
    Activations Density 0.090%

    No Known Activations