© 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. 55163
    Prev
    Next
    INDEX
    Explanations

    socio-economic development

    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
    å·²æĺ¯
    -0.10
    æİĩ
    -0.10
    åĢĻ
    -0.10
    Ñħа
    -0.10
    æį§
    -0.09
    ä»ĺè´¹
    -0.09
    è¦ĨçĽĸéĿ¢
    -0.09
    è¡Ķ
    -0.09
    ivol
    -0.09
     Ñĥзна
    -0.09
    POSITIVE LOGITS
     اÙĦتÙĨÙħÙĬØ©
    0.13
    åĨľä¸ļ
    0.12
     Development
    0.12
    Development
    0.11
     development
    0.11
    å¼Ģåıij
    0.10
    åıijå±ķ
    0.10
    å·¥ä¸ļåĮĸ
    0.10
    ç¹ģèį£
    0.10
    -development
    0.10
    Activations Density 0.102%

    No Known Activations