© 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. 58160
    Prev
    Next
    INDEX
    Explanations

    articles before nouns

    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
    åĽºåĮĸ
    -0.09
    orda
    -0.08
    clients
    -0.08
    ä¸Ŀ
    -0.08
    Enlarge
    -0.08
    uch
    -0.08
    -transitional
    -0.08
    棵
    -0.08
     coup
    -0.08
    è¯ħ
    -0.08
    POSITIVE LOGITS
    æĺı
    0.11
    好人
    0.10
     Mahm
    0.10
    路人
    0.09
    èĩªèº«çļĦ
    0.09
    ä¸Ģ个好çļĦ
    0.09
    骥
    0.09
    otive
    0.09
    å®ŀè´¨æĢ§
    0.09
    coe
    0.09
    Activations Density 0.055%

    No Known Activations