© 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. 17212
    Prev
    Next
    INDEX
    Explanations

    loan terms and periods

    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
    çģ¶
    -0.20
    STANCE
    -0.20
    ifice
    -0.19
    éĻ´
    -0.19
     Realt
    -0.19
    ä»İæł¹æľ¬ä¸Ĭ
    -0.18
    人å±ħ
    -0.18
     trÆ°á»Łng
    -0.18
     Gaw
    -0.18
     Baz
    -0.18
    POSITIVE LOGITS
    æĶ¾è¿Ľ
    0.23
    æ°ijçĶŁ
    0.22
     Retrie
    0.21
    æľŁéĻIJ
    0.21
    æ»ŀ
    0.21
    综
    0.21
    æ¼±
    0.21
    æĮģæľī
    0.20
    ä½¥
    0.20
    \views
    0.20
    Activations Density 0.008%

    No Known Activations