© 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. 10409
    Prev
    Next
    INDEX
    Explanations

    Cyprus and psoriasis

    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
     Sioux
    -0.18
    æ·«
    -0.18
    èĿĪ
    -0.17
    èĬĿåĬł
    -0.17
    лав
    -0.17
    Chicago
    -0.17
    verted
    -0.17
     Omaha
    -0.17
    IFORM
    -0.17
    纽约
    -0.17
    POSITIVE LOGITS
    ï¸ı
    0.23
    orsk
    0.20
    çĶŁçĶŁ
    0.19
    çĵľ
    0.19
    嶷
    0.18
    èĩ¾
    0.18
    IME
    0.17
    bek
    0.17
    unik
    0.17
    osed
    0.17
    Activations Density 0.006%

    No Known Activations