© 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. 39476
    Prev
    Next
    INDEX
    Explanations

    load and burden

    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
    åłĤ
    -0.10
    bens
    -0.09
    ius
    -0.08
    Declared
    -0.08
    æ´¾
    -0.08
    /Framework
    -0.08
    ardy
    -0.08
    åŀ£
    -0.08
     sund
    -0.08
     Desktop
    -0.08
    POSITIVE LOGITS
    è´Łæĭħ
    0.29
    æī¿æĭħ
    0.23
     burden
    0.22
    æĭħ
    0.19
    æī¿æĭħ责任
    0.19
     burdens
    0.19
    责任
    0.18
     responsibility
    0.17
    éĩįä»»
    0.17
    åĩıè½»
    0.17
    Activations Density 0.212%

    No Known Activations