© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-14B
    5. 20-RESID-BATCHTOPK-65K__L0-80
    7. 10343
    Prev
    Next
    INDEX
    Explanations

    foreign language

    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
    Negative Logits
    perhaps
    -0.25
    å½¼
    -0.22
     perhaps
    -0.21
    æĪĸ许
    -0.21
     sodom
    -0.20
    èĢĮéĿŀ
    -0.20
    å´©
    -0.20
    åŃĺåľ¨ä¸Ģå®ļ
    -0.19
     eher
    -0.19
    Perhaps
    -0.19
    POSITIVE LOGITS
    æĬĬæĪij
    0.29
    éĺ»ç¢į
    0.22
    NdEx
    0.22
    æŃ»äºĨ
    0.22
    说ä»Ģä¹Ī
    0.21
    çķ¶æĤ¨åľ¨
    0.20
    å±ħçĦ¶
    0.20
    sPid
    0.20
    mPid
    0.20
    GuidId
    0.20
    Activations Density 0.126%

    No Known Activations