© 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. 14249
    Prev
    Next
    INDEX
    Explanations

    development and planning

    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
    çĶŁäº§æĢ»
    -0.23
    ãĥĥãĤ·
    -0.23
    สมาà¸Ħม
    -0.22
    继ç»Ńä¿ĿæĮģ
    -0.22
    mant
    -0.22
    èµĦ产éĩįç»Ħ
    -0.21
    æł¸éħ¸æ£Ģæµĭ
    -0.21
    åįıä¼ļä¼ļéķ¿
    -0.21
    è¿Ļä¸Ģ天
    -0.21
    ç²¾ç¥ŀæĸĩæĺİ
    -0.21
    POSITIVE LOGITS
     mobil
    0.34
     local
    0.33
    åľ¨å½ĵåľ°
    0.32
    å½ĵåľ°
    0.31
    å½ĵåľ°çļĦ
    0.30
    æĶ¿çŃĸ
    0.28
     policy
    0.27
    åĽłåľ°åĪ¶å®ľ
    0.27
    æľ¬åľ°
    0.26
     NGOs
    0.25
    Activations Density 0.073%

    No Known Activations