© 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. 17134
    Prev
    Next
    INDEX
    Explanations

    social sharing links and services

    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
    è§Ħ
    -0.20
     parted
    -0.19
    PackageManager
    -0.19
    Schedulers
    -0.18
    inspect
    -0.18
     Ebook
    -0.18
    oldem
    -0.18
    ãĥijãĤ¤
    -0.18
    ined
    -0.18
    è°ĥåīĤ
    -0.18
    POSITIVE LOGITS
     visitors
    0.26
     visitor
    0.24
    åµĮ
    0.24
     Embed
    0.23
    æĿ¥è®¿
    0.22
    ä¹į
    0.22
     Visitors
    0.22
     embed
    0.21
    å¼ķæµģ
    0.21
    Embed
    0.20
    Activations Density 0.089%

    No Known Activations