© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 10544
    Prev
    Next
    INDEX
    Explanations

    Keystone species, XL, Chevron

    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
    鸨
    -0.11
    æĸ¥
    -0.11
    yar
    -0.09
    spot
    -0.09
    word
    -0.09
    à¹ģà¸ŀà¸Ĺย
    -0.09
    é«ĺ空
    -0.09
    AreaView
    -0.08
    tingham
    -0.08
     chÃłng
    -0.08
    POSITIVE LOGITS
     Gang
    0.10
    kits
    0.09
    é¢ı
    0.08
     trúc
    0.08
    ically
    0.08
    ril
    0.08
     gang
    0.08
    éĶ¹
    0.08
    atat
    0.08
     gangs
    0.08
    Activations Density 0.005%

    No Known Activations