© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 30992
    Prev
    Next
    INDEX
    Explanations

    Sri Lanka names and titles

    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
    Not in Any Lists

    No Comments

    Negative Logits
    æī£
    -0.09
    éĤ¨
    -0.09
    ç£ģ
    -0.09
    å¤ĩçĶ¨
    -0.09
    褶
    -0.09
    æĸ°å¼Ģ
    -0.08
    ç«ĭæ¡Ī
    -0.08
    à¹ĭ
    -0.08
    ä¸įåģľ
    -0.08
    å¤ĩ注
    -0.08
    POSITIVE LOGITS
     COPYRIGHT
    0.08
    Ùĥار
    0.08
    yar
    0.08
    å²Ĥ
    0.08
    elib
    0.08
    ම
    0.08
     Naw
    0.08
    ìĦ¼
    0.08
    æı
    0.08
     Sri
    0.08
    Activations Density 0.090%

    No Known Activations