© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 51527
    Prev
    Next
    INDEX
    Explanations

    military occupation and invasion

    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
    è¾Ī
    -0.11
    æĿĥçĽĬ
    -0.10
    erate
    -0.09
    estate
    -0.09
    artz
    -0.09
    ẩ
    -0.09
    æľīæĿĥ
    -0.09
    sem
    -0.09
    èĩªå¦Ĥ
    -0.09
    èģĮåĬ¡
    -0.08
    POSITIVE LOGITS
     shorthand
    0.08
    ucks
    0.08
    ãģ¾ãģ¾
    0.08
    纪å§Ķ
    0.08
    åĺĺ
    0.08
    raphic
    0.08
    åħ·
    0.08
    车åŀĭ
    0.08
     tolerant
    0.08
    glomer
    0.08
    Activations Density 0.012%

    No Known Activations