© 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. 16966
    Prev
    Next
    INDEX
    Explanations

    announcement or announce

    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
     /[
    -0.21
    æĮ¯åħ´
    -0.21
    èµ·æĿ¥äºĨ
    -0.19
    unta
    -0.19
    _TLS
    -0.18
    ç½®æį¢
    -0.18
     I
    -0.18
    é¹ħ
    -0.18
    æĹºçĽĽ
    -0.17
    æĪª
    -0.17
    POSITIVE LOGITS
    宣å¸ĥ
    0.41
     announcement
    0.35
    åħ¬å¸ĥ
    0.34
     announcing
    0.33
    åıijå¸ĥ
    0.32
     announce
    0.31
     ë°ľíijľ
    0.31
     announcements
    0.29
     announces
    0.28
    announcement
    0.28
    Activations Density 0.224%

    No Known Activations