© 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. 26241
    Prev
    Next
    INDEX
    Explanations

    clinical challenge

    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
    åķĦ
    -0.09
    åķĨéĩı
    -0.09
    èݽ
    -0.09
     оÑĦоÑĢмлен
    -0.08
    åħ®
    -0.08
    æ¬
    -0.08
    åĩĿ
    -0.08
    æ´½
    -0.08
    è¾ĥ好
    -0.08
    çĿ¹
    -0.08
    POSITIVE LOGITS
    æĮijæĪĺ
    0.38
     challenge
    0.29
    challenge
    0.27
     challenges
    0.26
     Challenge
    0.25
    Challenge
    0.25
     Challenges
    0.23
    _challenge
    0.21
     challenged
    0.20
     challenging
    0.20
    Activations Density 0.090%

    No Known Activations