© 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. 24242
    Prev
    Next
    INDEX
    Explanations

    honors and class

    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
    伪
    -0.10
    奸
    -0.10
    ÙĨب
    -0.09
    çīĩåĪ»
    -0.08
    åĿij
    -0.08
     tek
    -0.08
     pseudo
    -0.08
    å¼ĢæĿ¥
    -0.08
    éĢĶå¾Ħ
    -0.08
    chl
    -0.08
    POSITIVE LOGITS
    é©·
    0.09
     голов
    0.09
    ç²²
    0.09
    åħ¬æĬ¥
    0.09
    çŃĶ辩
    0.09
    idget
    0.09
    大纲
    0.09
    æĭ¿äºĨ
    0.09
    æľĢå¿«çļĦ
    0.09
    ones
    0.08
    Activations Density 0.004%

    No Known Activations