© 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. 40329
    Prev
    Next
    INDEX
    Explanations

    pronunciation of names or words

    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
     stellar
    -0.08
    æĸĩæĺİ
    -0.08
    bsp
    -0.08
    _pdu
    -0.08
    illet
    -0.08
    bane
    -0.08
    æĤį
    -0.08
    stell
    -0.07
     åķ
    -0.07
     stern
    -0.07
    POSITIVE LOGITS
     pronounced
    0.11
    æĺ¯æĢİæł·
    0.11
    读
    0.10
    ä»°
    0.10
    äºĨä¸Ģåı£
    0.10
    就读
    0.10
    念
    0.10
     Äijá»įc
    0.10
     pronounce
    0.09
    read
    0.09
    Activations Density 0.030%

    No Known Activations