© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 34416
    Prev
    Next
    INDEX
    Explanations

    click or press

    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
    仪
    -0.09
    .rf
    -0.09
    ÑĨин
    -0.09
    宣è¨Ģ
    -0.09
    éĻįèĩ³
    -0.08
    ify
    -0.08
    该åħ¬åı¸
    -0.08
    ift
    -0.08
    anko
    -0.08
    ìŀĦ
    -0.08
    POSITIVE LOGITS
    iele
    0.10
    ountry
    0.09
     ÄijÃło
    0.09
     Barker
    0.08
    壤
    0.08
     пеÑĢев
    0.08
    åģ¶
    0.08
    /cop
    0.08
    ä»Ģä¹Īåij¢
    0.08
     Fowler
    0.08
    Activations Density 0.052%

    No Known Activations