© 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. 10545
    Prev
    Next
    INDEX
    Explanations

    research and information contexts

    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
    /trunk
    -0.22
    Ä°LÄ°
    -0.21
    mens
    -0.20
    å¨Ī
    -0.19
    å±
    -0.19
    Confirmed
    -0.19
    @Module
    -0.19
    baÅŁÄ±
    -0.19
    ä»ĸå¦Ī
    -0.19
    .Disclaimer
    -0.18
    POSITIVE LOGITS
    çłĶ究
    0.38
    æŁ¥æī¾
    0.32
     research
    0.30
    课é¢ĺ
    0.28
    research
    0.26
     researching
    0.26
    æŁ¥éĺħ
    0.26
    éľĢè¦ģçĶ¨åĪ°
    0.25
    æĥ³æī¾
    0.25
     nghiên
    0.24
    Activations Density 0.068%

    No Known Activations