© 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. 51474
    Prev
    Next
    INDEX
    Explanations

    mask or plate

    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
    宿
    -0.09
    /welcome
    -0.09
    upy
    -0.08
    æłī
    -0.08
    两端
    -0.08
    æĮª
    -0.08
    çĶ¨äººåįķä½į
    -0.08
    thouse
    -0.08
    沮丧
    -0.08
    å°ıæŶåīį
    -0.08
    POSITIVE LOGITS
    模åħ·
    0.13
    oxy
    0.09
    çıŃåŃIJ
    0.09
    åİŁä»¶
    0.09
    åĪ¶ä½ľ
    0.09
    åİŁåĪĽ
    0.09
    æ¯į
    0.09
    original
    0.09
    åİŁèijĹ
    0.09
    è¿Ļå¼ł
    0.09
    Activations Density 0.173%

    No Known Activations