© 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. 48716
    Prev
    Next
    INDEX
    Explanations

    middle ages europe

    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
    åħŃå¹´
    -0.10
    åįģå¤ļå¹´
    -0.10
     bumper
    -0.09
    å·¥ä½ľçļĦ
    -0.09
     меÑĢопÑĢи
    -0.09
     единÑģÑĤв
    -0.09
    åĪĬçĻ»
    -0.09
    å·¥ä½ľç»ıéªĮ
    -0.09
    æİ¢
    -0.09
    åħļåĴĮ
    -0.09
    POSITIVE LOGITS
    欧洲
    0.12
     Europe
    0.11
     European
    0.10
    åľ°ä¸Ńæµ·
    0.09
     mono
    0.09
    éªİ
    0.09
    Europe
    0.09
    Mono
    0.08
     Europeans
    0.08
    èIJĮ
    0.08
    Activations Density 0.068%

    No Known Activations