© 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. 7721
    Prev
    Next
    INDEX
    Explanations

    methods and techniques

    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
    象
    -0.09
    æľīæĿ¡ä»¶çļĦ
    -0.09
    thr
    -0.09
    mand
    -0.09
    é¡ĺ
    -0.08
    çIJļ
    -0.08
     ÑĦин
    -0.08
    łģ
    -0.08
    sist
    -0.08
    å·´å·´
    -0.08
    POSITIVE LOGITS
    æīĭ段
    0.15
    å·¥åħ·
    0.13
     tools
    0.12
    åѦä¼ļäºĨ
    0.11
     dam
    0.10
     techniques
    0.09
    tools
    0.09
    è¦ģåѦä¼ļ
    0.09
    屿
    0.09
    ãĥĦ
    0.09
    Activations Density 0.239%

    No Known Activations