© 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. 21182
    Prev
    Next
    INDEX
    Explanations

    Deep learning and neural networks

    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
    æĹ¥å¸¸å·¥ä½ľ
    -0.09
    æīĺ
    -0.09
    åĪ»
    -0.09
    alus
    -0.09
    åŁĴ
    -0.09
    å¥ĵ
    -0.09
    athom
    -0.09
    ä»Ģä¹Īåij¢
    -0.09
    对çħ§
    -0.08
    举åĮĹ
    -0.08
    POSITIVE LOGITS
    快讯
    0.11
    大åݦ
    0.10
    究
    0.10
    çħĮ
    0.10
    å±
    0.09
    PARAM
    0.09
    ä¸ŃéĢĶ
    0.09
    8
    0.08
    空åīį
    0.08
    å±Ĥ次
    0.08
    Activations Density 0.163%

    No Known Activations