© 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. 19164
    Prev
    Next
    INDEX
    Explanations

    year or season

    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
    åĶ
    -0.10
    åĽŀåIJĪ
    -0.10
    ä¸ŃåĽ½æĶ¿åºľ
    -0.10
    åľ¨æѤä¹ĭåīį
    -0.10
    第ä¸ī次
    -0.09
    è¿Ļè¾ĪåŃIJ
    -0.09
    æı¡ä½ı
    -0.09
    ä»Ģä¹Īåij¢
    -0.09
    æ¯ıä¸Ģ天
    -0.09
    å¹³æŶ
    -0.09
    POSITIVE LOGITS
    unts
    0.09
     Synopsis
    0.09
    潦
    0.09
    åįģåŃĹ
    0.08
    ERY
    0.08
    lag
    0.08
    æĸĩåĮĸæĹħ游
    0.08
    áĥ¬
    0.08
     Ut
    0.08
    utor
    0.08
    Activations Density 0.020%

    No Known Activations