© 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. 37081
    Prev
    Next
    INDEX
    Explanations

    Japanese, expression, currencies

    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
    eer
    -0.08
    å°±æĺ¯è¿Ļæł·
    -0.08
    ä¹Łæĺ¯å¦ĤæѤ
    -0.08
    å¥
    -0.07
    ä½
    -0.07
    yna
    -0.07
    ä¸Ńå°ıåŀĭ
    -0.07
    icult
    -0.07
    onda
    -0.07
    iat
    -0.07
    POSITIVE LOGITS
    /or
    0.14
    ä»Ģä¹Īåij¢
    0.11
    åħ¶å®ĥ
    0.11
    åħ¶ä»ĸçļĦ
    0.11
    åĪ«çļĦ
    0.11
     기íĥĢ
    0.10
    phans
    0.10
    æĪijå°±
    0.10
    å¿ħçĦ¶
    0.09
    ä»ĸ人
    0.09
    Activations Density 0.310%

    No Known Activations