© 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. 17299
    Prev
    Next
    INDEX
    Explanations

    better or worse

    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
    ä¸įæŃ¢
    -0.20
    Resume
    -0.20
    èĽĽ
    -0.20
    cobra
    -0.19
    æĸ©
    -0.19
    hel
    -0.18
    helm
    -0.18
    ä¸Ģåıªæīĭ
    -0.18
    æıIJæ¡Ī
    -0.18
    resume
    -0.18
    POSITIVE LOGITS
    ä¸İåIJ¦
    0.21
    è¯Ħä»·
    0.20
    æĬ¹
    0.20
    PJ
    0.20
    ç²½
    0.19
    æī¦
    0.19
     Columbus
    0.19
    eton
    0.18
    ä¸Ģ楼
    0.18
    èĨı
    0.18
    Activations Density 0.022%

    No Known Activations