© 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. 16904
    Prev
    Next
    INDEX
    Explanations

    Southeast Asian place and film names

    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
    å¸Ŀ
    -0.11
    çī©åĵģ
    -0.09
    æĪijä¸įæĺ¯
    -0.09
    污泥
    -0.09
    ä¸ĸ
    -0.08
     اÙĦØ®ÙĦÙĬ
    -0.08
    isu
    -0.08
    积累
    -0.08
    ç¿Ĭ
    -0.08
    رÙĬ
    -0.08
    POSITIVE LOGITS
    ä¸Ģä¸Ģ
    0.09
    à¸Ŀ
    0.09
    åģ¥
    0.09
    olist
    0.09
    çģ
    0.08
    brig
    0.08
    /by
    0.08
    æ´Ĵ
    0.08
    飧æĢ§
    0.08
    orton
    0.08
    Activations Density 0.078%

    No Known Activations