© 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. 12122
    Prev
    Next
    INDEX
    Explanations

    legal decisions and court cases

    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
    Not in Any Lists

    No Comments

    Negative Logits
    æ¼Ķ
    -0.11
    çıī
    -0.10
    èħ°éĥ¨
    -0.10
    vas
    -0.10
    âĪ
    -0.09
    çł
    -0.09
    äºĮæīĭ
    -0.09
    asant
    -0.08
    æĸĩåŃĹ
    -0.08
    éĸ£
    -0.08
    POSITIVE LOGITS
    éŨæĪ·
    0.10
    æĹ¥äº§
    0.09
    kiem
    0.09
    ç¾¼
    0.09
    滥
    0.09
    .sess
    0.09
    æįı
    0.08
    åĪ¨
    0.08
    伤å¿ĥ
    0.08
    ç¥ŀåĻ¨
    0.08
    Activations Density 0.058%

    No Known Activations