© 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. 37386
    Prev
    Next
    INDEX
    Explanations

    preventing or promoting positive outcomes

    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
    TRS
    -0.09
    æľºç»Ħ
    -0.08
    Emer
    -0.08
    é¢ijçİĩ
    -0.08
    eature
    -0.08
    ä¸Ģ次
    -0.08
    æݧèĤ¡éĽĨåĽ¢
    -0.08
    ç»ģ
    -0.08
     Epstein
    -0.08
    frequency
    -0.08
    POSITIVE LOGITS
    ä¿ĥè¿Ľ
    0.10
    å¢ŀè¿Ľ
    0.10
    åĮºåĨħ
    0.09
     education
    0.09
    æĻ®æĥł
    0.09
    贯彻
    0.09
    ainer
    0.09
    èį¼
    0.09
    æİ¨è¿Ľ
    0.09
    ä¿ĿæĬ¤
    0.08
    Activations Density 0.153%

    No Known Activations