© 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. 38170
    Prev
    Next
    INDEX
    Explanations

    adverbs modifying subsequent words

    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
    æīĢæıIJä¾Ľ
    -0.10
    åıįæĺłåĩº
    -0.09
    æīĢæıIJä¾ĽçļĦ
    -0.09
    ivic
    -0.08
     entire
    -0.08
    è¿Ļ个ä¸ĸçķĮ
    -0.08
    è½»è½»åľ°
    -0.08
    é³³
    -0.08
    Spoiler
    -0.08
    ä¸ĭæĿ¥
    -0.08
    POSITIVE LOGITS
    çļĦ人æĿ¥è¯´
    0.10
    ourage
    0.09
    zing
    0.09
    人éĥ½
    0.08
    åIJīåĪ©
    0.08
    Formula
    0.08
    å¢Ļ
    0.08
    å¥łåŁº
    0.08
    èĢĮåıĪ
    0.08
    -needed
    0.08
    Activations Density 0.157%

    No Known Activations