© 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. 11606
    Prev
    Next
    INDEX
    Explanations

    business lunch or dinner

    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
    ä»Ģä¹Īåij¢
    -0.10
    æĬĬè¿Ļ个
    -0.10
    é¢Ĩçķ¥
    -0.10
    ãįī
    -0.10
    çĢı
    -0.10
    ãĮ¢
    -0.09
    çĦļ
    -0.09
    ãĬĻ
    -0.09
    碧æ¡Ĥ
    -0.09
    ãĤ¢ãĥ¡ãĥª
    -0.09
    POSITIVE LOGITS
    éĩĩçŁ¿çŃī
    0.10
    ãģĿãĤĤ
    0.07
    åıĪæĺ¯
    0.07
    Ø£Ùĩد
    0.07
     Generally
    0.07
    âĭ°
    0.06
    mpp
    0.06
     )↵↵↵↵↵↵↵↵
    0.06
     etc
    0.06
    Ø£ÙģÙĦ
    0.06
    Activations Density 1.871%

    No Known Activations