© 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. 712
    Prev
    Next
    INDEX
    Explanations

    budget deficit

    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
    渡
    -0.12
    çļĦä¸ĢéĿ¢
    -0.09
    æĭ¢
    -0.09
     вообÑīе
    -0.09
    ÑģоÑĢ
    -0.09
    审çIJĨ
    -0.08
    管çIJĨåĬŀæ³ķ
    -0.08
    urv
    -0.08
    strstr
    -0.08
    åĩ¡
    -0.08
    POSITIVE LOGITS
    å¹ħ度
    0.11
    éķ³
    0.10
    é¼ĵ
    0.10
    溢价
    0.10
    è®®
    0.10
    é¼
    0.09
     deficit
    0.09
     rep
    0.09
    åįĬå¹´
    0.09
    åħŃåIJĪ
    0.09
    Activations Density 0.053%

    No Known Activations