© 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. 35249
    Prev
    Next
    INDEX
    Explanations

    capital and economics

    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
    ople
    -0.09
    çIJĨæĢ§
    -0.09
    å¤ĸåĽ½äºº
    -0.09
    åĻ¤
    -0.08
    /support
    -0.08
    æĮĩå¼ķ
    -0.08
    æĪ´
    -0.08
    æı´åĬ©
    -0.08
     Belgi
    -0.08
    AffineTransform
    -0.08
    POSITIVE LOGITS
    ument
    0.09
    è¿Ļä¸ĢåĪ»
    0.09
     Waterloo
    0.09
    ä¸įèµ·
    0.09
    ä¾ī
    0.09
    rou
    0.09
    æ¯Ĵ
    0.08
    åĪ°æŶåĢĻ
    0.08
    蹩
    0.08
    人çĶŁçļĦ
    0.08
    Activations Density 0.122%

    No Known Activations