© 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. 12395
    Prev
    Next
    INDEX
    Explanations

    pension law

    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
    满æĢĢ
    -0.10
    ç£Ķ
    -0.10
    éŀį
    -0.10
    满èĦ¸
    -0.09
     обоÑĢ
    -0.09
    æĶ¾æĿ¾
    -0.09
    ä½ĵæ£Ģ
    -0.09
     INTERN
    -0.09
     municipalities
    -0.09
    _IMPLEMENT
    -0.09
    POSITIVE LOGITS
    çķĻç»Ļ
    0.09
    åıįèĢĮ
    0.09
    æ±ł
    0.08
    .Unmarshal
    0.08
    -sharing
    0.08
    ä¸įåĪĨ
    0.08
    迹
    0.08
    寮
    0.08
    ITE
    0.08
     gam
    0.08
    Activations Density 0.057%

    No Known Activations