© 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. 59103
    Prev
    Next
    INDEX
    Explanations

    financial deficit and borrowing

    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
    è´«
    -0.08
    åįī
    -0.08
    ä¹į
    -0.08
    åĨ»
    -0.08
    ector
    -0.08
    ä¸ĢåıĮ
    -0.08
    æł¸åĩĨ
    -0.08
    çħ½
    -0.08
    çĨŁ
    -0.07
    æĸĩèīº
    -0.07
    POSITIVE LOGITS
    æĭĬ
    0.09
    éļIJ
    0.09
    继æī¿
    0.09
    éļIJå½¢
    0.09
    éļ±
    0.09
    orr
    0.09
     borrowed
    0.08
    çªĸ
    0.08
     ÙĪعد
    0.08
    åĨ¶éĩij
    0.08
    Activations Density 0.165%

    No Known Activations