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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 37200
    Prev
    Next
    INDEX
    Explanations

    economic growth trends

    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
    对æĪij们
    -0.09
    ÑģÑĤо
    -0.09
     Holl
    -0.09
    èģĶ缣
    -0.09
    æĶ¯éĥ¨
    -0.09
    æĺ¯æĪij们
    -0.09
    æĪijæł¡
    -0.08
    表æī¬
    -0.08
    uce
    -0.08
    éªij士
    -0.08
    POSITIVE LOGITS
     GDP
    0.11
    æľ¬åĽ½
    0.11
    æĶ¿åºľ
    0.10
    åŁºç¡Ģ设æĸ½
    0.10
     infrastructure
    0.10
     citizens
    0.10
    åħ¬æ°ij
    0.09
     imports
    0.09
     Minister
    0.09
     Ministry
    0.09
    Activations Density 0.253%

    No Known Activations