© 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. 10420
    Prev
    Next
    INDEX
    Explanations

    vasoconstriction, smooth muscles

    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
    æĭIJ
    -0.21
    ationally
    -0.21
    vit
    -0.20
    à¸ļำ
    -0.20
     visita
    -0.20
    é¼IJ
    -0.20
    èĢĥè¯ģ
    -0.20
    㶲
    -0.19
    çĶŁäº§åĬĽ
    -0.19
    (strategy
    -0.19
    POSITIVE LOGITS
    æĶ¶ç¼©
    0.22
    åłµå¡ŀ
    0.20
    /sm
    0.20
    æĽ²
    0.19
    PMC
    0.19
     lax
    0.19
    æī©å¼ł
    0.19
    ä¸ĵåijĺ
    0.19
    ules
    0.19
    涣
    0.19
    Activations Density 0.212%

    No Known Activations