© 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. 17264
    Prev
    Next
    INDEX
    Explanations

    football league seasons

    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
     hob
    -0.21
    ews
    -0.21
    ammen
    -0.19
    æī¹æ¬¡
    -0.18
    icter
    -0.18
    ritos
    -0.18
     Merrill
    -0.18
    åĩºå¤Ħ
    -0.18
     department
    -0.18
    fir
    -0.18
    POSITIVE LOGITS
    åĩ¤åĩ°
    0.20
    çIJļ
    0.20
    çİ¥
    0.20
     ÄijÃłn
    0.19
     Initialized
    0.19
    å®ĺæĸ¹ç½ijç«Ļ
    0.19
    å¥ĩèij©
    0.19
    Billy
    0.19
     @[
    0.19
    æĪIJç«ĭ以æĿ¥
    0.18
    Activations Density 0.029%

    No Known Activations