© 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. 47500
    Prev
    Next
    INDEX
    Explanations

    bonds, debt, and notes

    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
    袪
    -0.09
    zzo
    -0.08
    ahr
    -0.08
    å°ıåºĹ
    -0.08
    æŀģ
    -0.08
    æĸ¹è¨Ģ
    -0.08
    åĸĻ
    -0.08
    coma
    -0.08
    çĻ½æĸij
    -0.08
    branches
    -0.07
    POSITIVE LOGITS
    åıijè¡Į
    0.13
    åħ¬å¼Ģåıijè¡Į
    0.13
    åĢºåĪ¸
    0.13
    ç¿ķ
    0.09
    .Promise
    0.09
    aters
    0.09
    æĮĩåIJij
    0.09
     bonds
    0.09
    çŃĶåºĶ
    0.09
     bond
    0.08
    Activations Density 0.042%

    No Known Activations