© 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. 17079
    Prev
    Next
    INDEX
    Explanations

    prepositions and dates

    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
    åľ°æ¯¯
    -0.18
    寻
    -0.18
    å½¼
    -0.18
     desp
    -0.18
     ká»ĭp
    -0.18
    ä¹ŁæĽ¾
    -0.17
    循
    -0.17
    ÙģÙĬÙĨ
    -0.17
    /mm
    -0.17
     tantr
    -0.17
    POSITIVE LOGITS
    ä¸Ģ举
    0.21
    slice
    0.19
    ä¸Ģå¥Ĺ
    0.19
    çķĻä¸ĭ
    0.19
    西éĥ¨
    0.18
    å®ĺæĸ¹ç½ijç«Ļ
    0.18
    åľ¨å½ĵåľ°
    0.18
    rpc
    0.18
    GES
    0.18
     setResult
    0.18
    Activations Density 0.069%

    No Known Activations