© 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. 38032
    Prev
    Next
    INDEX
    Explanations

    stop / stopping / deter

    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
    æ¼Ķ
    -0.09
    èıĺ
    -0.09
    é»ij马
    -0.09
    æŀ¶åŃIJ
    -0.09
    ä¿ĺ
    -0.09
    ale
    -0.08
    èĤ¯
    -0.08
    ä¸Ģæīĭ
    -0.08
    大佬
    -0.08
     Cliff
    -0.08
    POSITIVE LOGITS
    æĢĢ念
    0.10
    æĤªãģĦ
    0.09
    Foundation
    0.09
     пÑĢид
    0.09
     ÅĽrodk
    0.09
    hic
    0.09
    ÑİÑī
    0.09
    GRP
    0.09
    -demand
    0.08
     uncont
    0.08
    Activations Density 0.009%

    No Known Activations