© 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. 10401
    Prev
    Next
    INDEX
    Explanations

    dates of decisions or rehearings

    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
    orp
    -0.21
    opal
    -0.20
    æĥŁ
    -0.19
    Startup
    -0.18
     nationalism
    -0.18
    gif
    -0.18
     recip
    -0.18
    sted
    -0.18
     summ
    -0.18
    å¥ī
    -0.18
    POSITIVE LOGITS
    èĻ¬
    0.25
    åĿĩè¡¡
    0.19
    说çļĦæĺ¯
    0.19
    åIJį称
    0.19
    reds
    0.19
    åĿŀ
    0.19
    ulen
    0.18
    æī¹åĩĨ
    0.18
    æľĪä¸Ń
    0.18
    éªĸ
    0.18
    Activations Density 0.075%

    No Known Activations