© 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. 8345
    Prev
    Next
    INDEX
    Explanations

    million or billion

    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
    éĵº
    -0.11
    VEL
    -0.10
    èµ³
    -0.09
    achable
    -0.09
    ixin
    -0.08
    ä¿Ŀåģ¥
    -0.08
    æŃ¥æŃ¥
    -0.08
     penny
    -0.08
     san
    -0.08
    æī¿æĭħ
    -0.08
    POSITIVE LOGITS
    çĻ¾ä¸ĩ
    0.11
    åĬ¨éĿĻ
    0.10
    åºŀ大çļĦ
    0.09
    æݸ
    0.09
    ÑĪка
    0.09
    vette
    0.09
    åįĥä¸ĩ
    0.09
    nga
    0.08
     billion
    0.08
    è±¹
    0.08
    Activations Density 0.054%

    No Known Activations