© 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. 17008
    Prev
    Next
    INDEX
    Explanations

    date ranges

    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
    Not in Any Lists

    No Comments

    Negative Logits
    .Safe
    -0.22
    åĬ¨æīĭ
    -0.21
    æŁ¥éªĮ
    -0.21
    ·»
    -0.20
    burg
    -0.19
     pans
    -0.19
    è¢ĸ
    -0.19
    TEAM
    -0.19
    볨
    -0.19
    inds
    -0.18
    POSITIVE LOGITS
    ipple
    0.23
    绯
    0.20
     mer
    0.20
    éĿ¢éĥ¨
    0.19
    æĮº
    0.19
     Ùħت
    0.19
    åŃ¢
    0.19
    ä¹ĭ声
    0.18
    åIJĥå¾Ĺ
    0.18
     Pretty
    0.18
    Activations Density 0.045%

    No Known Activations