© 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. 37823
    Prev
    Next
    INDEX
    Explanations

    preposition followed by noun or time

    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
    éģ½
    -0.09
     Bent
    -0.09
    è¿Ľä¸ĢæŃ¥
    -0.09
    ä»»ä½ķå½¢å¼ı
    -0.09
    èī²ãĢħ
    -0.09
    骧
    -0.08
    ä¾®
    -0.08
     Bentley
    -0.08
    å®ĵ
    -0.08
    ä¹ŁçŁ¥éģĵ
    -0.08
    POSITIVE LOGITS
    æģ°æģ°
    0.11
    寿
    0.10
    æĺ¯åľ¨
    0.10
    åı«åģļ
    0.09
    ä½ĵçİ°åľ¨
    0.09
     пÑĢиÑĩ
    0.09
     çı
    0.09
    壽
    0.08
    é¢ľ
    0.08
    èİ«è¿ĩäºİ
    0.08
    Activations Density 0.163%

    No Known Activations