© 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. 60695
    Prev
    Next
    INDEX
    Explanations

    relative pronouns introducing clauses

    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
    èİ«æĸ¯
    -0.09
    æĪĸèĢħ说
    -0.09
    绾
    -0.08
    inking
    -0.08
    mo
    -0.08
    åijĬè¯īæĪij
    -0.08
     *****
    -0.08
    çļĦ姿æĢģ
    -0.08
    qr
    -0.08
     peace
    -0.08
    POSITIVE LOGITS
    衽
    0.11
    åįģåĪĨéĩįè¦ģ
    0.10
    æľĢéĩįè¦ģ
    0.09
    顯
    0.09
    æĺ¾
    0.09
    /uploads
    0.09
    OMPI
    0.09
     Ñģобой
    0.09
    JOR
    0.09
    åľ°å¸¦
    0.09
    Activations Density 0.634%

    No Known Activations