© 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. 55123
    Prev
    Next
    INDEX
    Explanations

    duty and obligation

    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
    erah
    -0.09
     Yok
    -0.08
    éī´å®ļ
    -0.08
    ä¼´
    -0.08
     Liv
    -0.08
     nominee
    -0.08
    arme
    -0.07
    agen
    -0.07
    nam
    -0.07
    ARC
    -0.07
    POSITIVE LOGITS
    ä¹īåĬ¡
    0.24
     obligation
    0.20
    義åĭĻ
    0.20
     obligations
    0.18
     обÑıзан
    0.16
     duty
    0.16
     duties
    0.13
     obligated
    0.13
    å±¥èģĮ
    0.12
    责任
    0.12
    Activations Density 0.155%

    No Known Activations