© 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. 1870
    Prev
    Next
    INDEX
    Explanations

    investment banking and management

    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
    è¡ĮæĶ¿æī§æ³ķ
    -0.09
    ä¾ĽåºĶéĵ¾
    -0.09
     Phelps
    -0.08
     Emperor
    -0.08
    社ä¼ļæķĪçĽĬ
    -0.08
    è´´
    -0.08
    åŁºå±Ĥ
    -0.08
    æĮ¨
    -0.08
    è²¼
    -0.08
    èĦ
    -0.08
    POSITIVE LOGITS
    è¯ģåĪ¸æĬķèµĦ
    0.15
    è¯ģåĪ¸
    0.15
    çIJĨ财产åĵģ
    0.13
    èĤ¡ç¥¨
    0.13
     securities
    0.13
     اÙĦأسÙĩÙħ
    0.11
     Securities
    0.11
    æĬķèµĦ
    0.11
    æĬķè³ĩ
    0.11
    两åıª
    0.11
    Activations Density 0.151%

    No Known Activations