© 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. 17138
    Prev
    Next
    INDEX
    Explanations

    indenture, forced labor, worked

    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
     moment
    -0.20
    coc
    -0.20
    询
    -0.19
     lle
    -0.19
    稳å®ļæĢ§
    -0.18
     diagonal
    -0.18
     hazırlan
    -0.18
    ä¸Ģ度
    -0.18
     kenn
    -0.18
     Pause
    -0.18
    POSITIVE LOGITS
    èĩ´æķ¬
    0.23
    plib
    0.23
    olar
    0.21
    iaz
    0.21
    躲éģ¿
    0.20
    èµİ
    0.20
    elib
    0.20
    .ast
    0.19
    _subtype
    0.19
     доб
    0.19
    Activations Density 0.008%

    No Known Activations