© 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. 10572
    Prev
    Next
    INDEX
    Explanations

    have followed by a description

    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
    å®ĥçļĦ
    -0.35
     itself
    -0.33
     its
    -0.30
     Its
    -0.27
    Its
    -0.26
    æĬĬå®ĥ
    -0.26
    让å®ĥ
    -0.24
    åĽłä¸ºå®ĥ
    -0.24
    å®ĥæĺ¯
    -0.23
    为åħ¶
    -0.23
    POSITIVE LOGITS
     themselves
    0.57
    åIJĦèĩªçļĦ
    0.49
    åIJĦèĩª
    0.46
     Ñģами
    0.34
     respective
    0.28
     selves
    0.26
     thems
    0.25
    ÅĽmy
    0.25
     עצ×ŀ×Ŀ
    0.24
    å½¼æѤ
    0.24
    Activations Density 0.419%

    No Known Activations