© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 35137
    Prev
    Next
    INDEX
    Explanations

    federal government

    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
    çªł
    -0.08
    rete
    -0.08
    æķ£æĪ·
    -0.08
    礼仪
    -0.08
    è¿Ļä¸ĢçĤ¹
    -0.07
    åĪĹåħ¥
    -0.07
    æ¯Ĵ
    -0.07
    âĸ¼
    -0.07
    anie
    -0.07
    åĨ¤
    -0.07
    POSITIVE LOGITS
    人æ°ijæĶ¿åºľ
    0.19
    æĶ¿åºľ
    0.19
    æĶ¿æĿĥ
    0.15
     government
    0.15
     governments
    0.15
    å½ĵå±Ģ
    0.14
    åľ°æĸ¹æĶ¿åºľ
    0.14
    æĶ¿åºľéĥ¨éŨ
    0.14
    å½ĵåľ°æĶ¿åºľ
    0.13
     пÑĢавиÑĤелÑĮ
    0.13
    Activations Density 0.132%

    No Known Activations