© 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. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 7778
    Prev
    Next
    INDEX
    Explanations

    Connecticut school events

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    adamkarvonen/qwen3-32b-saes/saes_Qwen_Qwen3-32B_batch_top_k/resid_post_layer_32
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    趵
    -0.10
     Minnesota
    -0.10
    沩
    -0.10
    èį¥
    -0.09
    Minnesota
    -0.09
    æ´±
    -0.09
     Egyptian
    -0.08
    æĺĨæĺİ
    -0.08
    é©»
    -0.08
     Alberta
    -0.08
    POSITIVE LOGITS
    æ³°å·ŀ
    0.12
    ç»įåħ´
    0.12
    åı°å·ŀ
    0.12
     Hartford
    0.10
     Yale
    0.10
    æ»Ķ
    0.10
     اÙĦتÙĪÙĨسÙĬ
    0.10
     Connecticut
    0.10
    ilia
    0.10
    æ±ŁéŨ
    0.10
    Activations Density 0.193%

    No Known Activations