© 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. 16672
    Prev
    Next
    INDEX
    Explanations

    chronic conditions

    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
     Zy
    -0.09
     chÃŃnh
    -0.09
    ä¹ĺ车
    -0.08
    ä»ĩ
    -0.08
    çİĭèĢħ
    -0.08
    çŁŃçŁŃ
    -0.08
    亲åıĭ
    -0.08
    Lik
    -0.08
    ç»ĨåĪĻ
    -0.08
    竣工
    -0.08
    POSITIVE LOGITS
    persistent
    0.10
    æĮģä¹ħ
    0.10
    稳å®ļ
    0.10
    åĮĸçļĦ
    0.09
    .fig
    0.09
     неÑģк
    0.09
     GANG
    0.09
    èĽ©
    0.09
     McCart
    0.08
    稳å®ļçļĦ
    0.08
    Activations Density 0.100%

    No Known Activations