© 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. 6107
    Prev
    Next
    INDEX
    Explanations

    being + adjective

    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
    TOR
    -0.10
    å¾Īå¿«
    -0.10
    å®ĮåĸĦçļĦ
    -0.09
    å½Ĵå±ŀ
    -0.09
    æĭīæĸ¯
    -0.09
    .us
    -0.09
    ç§ijå°Ķ
    -0.09
    ç½²
    -0.09
    Dump
    -0.09
    尽快
    -0.09
    POSITIVE LOGITS
    çħŀ
    0.11
    åħ¬æĬ¥
    0.10
    浪漫
    0.10
    磾
    0.10
    龸éģĵ
    0.09
    ä¹ĸ
    0.09
    è°ĥçļ®
    0.09
    èĢį
    0.09
     stubborn
    0.09
    麻çĥ¦
    0.09
    Activations Density 0.048%

    No Known Activations