© 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. 26682
    Prev
    Next
    INDEX
    Explanations

    social responsibility duty

    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
     Par
    -0.09
    çŃ¹éĽĨ
    -0.08
    Par
    -0.08
     conv
    -0.08
    ä½łä»¥ä¸º
    -0.08
    èµŀæī¬
    -0.08
     Parsons
    -0.08
    ç¼ij
    -0.08
    å¢ŀ
    -0.08
    çľĭæĿ¥
    -0.08
    POSITIVE LOGITS
    责任
    0.25
    çļĦ责任
    0.23
     responsibility
    0.21
    责任æĦŁ
    0.21
    責任
    0.21
     Responsibility
    0.19
    社ä¼ļ责任
    0.18
    èĤ©è´Ł
    0.18
     Responsibilities
    0.18
     duty
    0.17
    Activations Density 0.051%

    No Known Activations