© 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. 15918
    Prev
    Next
    INDEX
    Explanations

    not precedential

    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
    å½»åºķ
    -0.27
    å¾¹
    -0.24
    åIJĦ个æĸ¹éĿ¢
    -0.22
    èĪĦ
    -0.21
    åĩĨå¤ĩ好
    -0.20
    /operator
    -0.20
    ä¹°åĪ°
    -0.20
    ä¸Ģ个好çļĦ
    -0.20
    度è¿ĩ
    -0.19
    åģī
    -0.19
    POSITIVE LOGITS
    æĸ°éĹ»åıijå¸ĥ
    0.23
    gue
    0.23
    uned
    0.22
    æĬķ稿
    0.20
    ÑĢаÐ
    0.20
    æı´
    0.20
    èĭ¥æľī
    0.20
    æ¯ıéĢ¢
    0.20
    主æŨ
    0.19
     postings
    0.19
    Activations Density 0.085%

    No Known Activations