© 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. 17132
    Prev
    Next
    INDEX
    Explanations

    European Union

    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
    íŀĪ
    -0.18
    bread
    -0.17
    ä¸ŃåĽ½äººæ°ij
    -0.17
    ми
    -0.16
    ย
    -0.16
    è´¹
    -0.16
    /to
    -0.15
    pieces
    -0.15
    潺
    -0.15
    Py
    -0.15
    POSITIVE LOGITS
    -wide
    0.28
    ropa
    0.26
    wide
    0.22
    æĺī
    0.22
    æĪIJåijĺåĽ½
    0.20
     dozen
    0.20
    èĮĥåĽ´åĨħ
    0.19
    è±ķ
    0.18
    åIJĦåĽ½
    0.18
    å¿«ä¸ī
    0.17
    Activations Density 0.013%

    No Known Activations