© 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. 12426
    Prev
    Next
    INDEX
    Explanations

    challenge, challenged, challenges

    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
    onica
    -0.09
    Ó¯
    -0.09
     Buckley
    -0.09
    posix
    -0.09
    _misc
    -0.09
    ä¹IJ
    -0.09
    ç¿ħèĨĢ
    -0.09
    ADIO
    -0.09
     Carp
    -0.08
    æѧ
    -0.08
    POSITIVE LOGITS
    æĮijæĪĺ
    0.20
     challenge
    0.14
    æIJ¦
    0.13
     challenges
    0.13
    æĮij
    0.12
    æĮijè¡ħ
    0.12
     Challenge
    0.12
    challenge
    0.11
     challenging
    0.11
     challenged
    0.11
    Activations Density 0.054%

    No Known Activations