© 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. 29930
    Prev
    Next
    INDEX
    Explanations

    adverbs ending in -ly

    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
    èļ©
    -0.09
     aff
    -0.08
    wap
    -0.08
     gib
    -0.08
    åĨĽäºĭ
    -0.08
    اض
    -0.08
    è¦ģåľ¨
    -0.08
    zig
    -0.07
    led
    -0.07
    adas
    -0.07
    POSITIVE LOGITS
    æķ´ä¸ªäºº
    0.10
     ÙĦÙĦغاÙĬØ©
    0.10
    çijķçĸµ
    0.09
     جدا
    0.09
    åŀ¢
    0.09
     enough
    0.09
    æĽ´èĥ½
    0.09
    佬
    0.09
    .Handle
    0.09
    åĢĺ
    0.09
    Activations Density 0.115%

    No Known Activations