© 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. 59282
    Prev
    Next
    INDEX
    Explanations

    judicial custody

    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
    ulous
    -0.10
    åĪĨæĺİ
    -0.09
    襻
    -0.09
    å³Ļ
    -0.09
    ulle
    -0.09
    éĶŁ
    -0.09
    饴
    -0.08
    é¢Ħè§ģ
    -0.08
    ulations
    -0.08
    åĩŃä»Ģä¹Ī
    -0.08
    POSITIVE LOGITS
     ÑģÑĤан
    0.09
    çĻ½éĽª
    0.09
    å¼ıçļĦ
    0.09
     пÑĢедÑģÑĤавлен
    0.09
     bat
    0.09
    anner
    0.09
    ÑĢо
    0.08
    ä¼ļè®®
    0.08
    äºĨ大éĩıçļĦ
    0.08
     sợ
    0.08
    Activations Density 0.007%

    No Known Activations