© 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. 17238
    Prev
    Next
    INDEX
    Explanations

    specialty, specialties, specialist, specialists

    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
    Submitting
    -0.21
    æ©Ħ
    -0.20
    tails
    -0.20
    尾巴
    -0.20
    contained
    -0.20
     tails
    -0.19
    ç³»åĪĹ产åĵģ
    -0.19
    æĪIJè´¥
    -0.19
    æķŀå¼Ģ
    -0.19
    lest
    -0.18
    POSITIVE LOGITS
    ä¸ĵç§ij
    0.30
    ä¸ĵéŨ
    0.29
     specialties
    0.27
     specialty
    0.26
    ä¸ĵ注äºİ
    0.26
     specialist
    0.25
    ä¸ĵ项
    0.24
    ä¸ĵ注
    0.23
     specialization
    0.23
     specialists
    0.23
    Activations Density 0.035%

    No Known Activations