© 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. 36705
    Prev
    Next
    INDEX
    Explanations

    burrito, bowl, kimbap, food types

    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
     dist
    -0.09
    ä¸Ŀ绸ä¹ĭè·¯
    -0.08
    èݺ
    -0.08
    anne
    -0.08
    jab
    -0.08
    riel
    -0.08
     tro
    -0.08
     пÑĢедÑģÑĤавлÑı
    -0.08
     REGARD
    -0.08
    zed
    -0.08
    POSITIVE LOGITS
    ä¿Ŀå¯Ĩ
    0.09
    æµ·æ·Ģ
    0.09
    å¤ĸæı´
    0.09
    çĭ¸
    0.09
     shelters
    0.08
    æ²»å®ī
    0.08
    æĮŁ
    0.08
     shelter
    0.08
    类产åĵģ
    0.08
    WithType
    0.08
    Activations Density 0.006%

    No Known Activations