© 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. 10563
    Prev
    Next
    INDEX
    Explanations

    `2000-01-01 +0000`

    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
    该
    -0.24
    ä¸įåIJĮçļĦ
    -0.20
    /tr
    -0.20
    on
    -0.20
    æīĭä¸ŃçļĦ
    -0.19
    erek
    -0.19
    ty
    -0.19
    -e
    -0.19
    çļĦ好
    -0.19
    çļĦä¸įåIJĮ
    -0.19
    POSITIVE LOGITS
    )did
    0.22
    å¥¥åľ°
    0.22
     uLocal
    0.22
     fkk
    0.22
    _ComCallableWrapper
    0.20
    ä¸īç§įèģĮä¸ļ
    0.20
    à¸Ńาย
    0.20
    ¡´
    0.20
     sourceMapping
    0.20
    .addComponent
    0.19
    Activations Density 0.019%

    No Known Activations