© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 20679
    Prev
    Next
    INDEX
    Explanations

    actions ending in -ing

    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
    ç®ĢåįķçļĦ
    -0.09
    ä»ħ代表
    -0.09
    icha
    -0.09
    ä¸Ģ度
    -0.09
    è¿Ļ让
    -0.09
    çľ¼æ³ª
    -0.09
    彦
    -0.08
    æĪı
    -0.08
    èĨı
    -0.08
    éĢ¸
    -0.08
    POSITIVE LOGITS
    说çĿĢ
    0.12
    åIJĦ个æĸ¹éĿ¢
    0.09
    æĥ³çĿĢ
    0.09
    寸
    0.09
    åĨĻçĿĢ
    0.09
    å¿ĻçĿĢ
    0.08
     пÑĢиÑĩ
    0.08
    享åıĹ
    0.08
    wins
    0.08
    æĭĵ宽
    0.08
    Activations Density 0.104%

    No Known Activations