© 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. 9263
    Prev
    Next
    INDEX
    Explanations

    sports actions and positions

    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
    æī©å®¹
    -0.12
    è¢Ĵ
    -0.10
    对ä»ĸ
    -0.09
    å¯¹æľªæĿ¥
    -0.09
    对ä»ĸ们
    -0.09
    亲åĪĩ
    -0.09
    说æľį
    -0.09
    mpl
    -0.08
    æķĪåĬĽ
    -0.08
    æIJģ
    -0.08
    POSITIVE LOGITS
    empor
    0.09
    à¸Īา
    0.09
    IPAddress
    0.08
    æ±ŁåįĹ
    0.08
    æĻ®
    0.08
    วà¸Ļ
    0.08
    apon
    0.08
    åĪĩæĪIJ
    0.08
     Fay
    0.08
    èĭŀ
    0.08
    Activations Density 0.035%

    No Known Activations