© 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. 20846
    Prev
    Next
    INDEX
    Explanations

    charge or charging

    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
     ÑģÑĤоим
    -0.10
    tru
    -0.09
     bri
    -0.09
    èĢ½
    -0.09
    è¯Ħ论
    -0.09
    æĹ©
    -0.09
    导å¸Ī
    -0.09
    黾
    -0.09
    éĤ£ä»½
    -0.09
    è´»
    -0.09
    POSITIVE LOGITS
    als
    0.08
    ve
    0.08
    å¸Ļ
    0.08
    ä¸ĢèĪ¬äºº
    0.08
    ibel
    0.08
    è¾ħ
    0.07
    à¸Īำหà¸Ļ
    0.07
    ä¸Ģæĸ¹
    0.07
    mart
    0.07
    æĸIJ
    0.07
    Activations Density 0.018%

    No Known Activations