© 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. 2213
    Prev
    Next
    INDEX
    Explanations

    world war battlefields warfare

    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
    带éĺŁ
    -0.10
    èĪŁ
    -0.10
    趸
    -0.09
    ayar
    -0.09
    é³ı
    -0.08
    åħ¥é©»
    -0.08
    à¸ij
    -0.08
    èĪ«
    -0.08
    æİĮ声
    -0.08
    å¸ĤåĢ¼
    -0.08
    POSITIVE LOGITS
    ä¸Ńæĸ°
    0.10
    ä¼ĺåĬ¿
    0.09
    éıĸ
    0.09
    æ¶ĪèĢĹ
    0.09
    èĢĹ
    0.09
    è±ķ
    0.09
    åįłæľī
    0.09
     Wellington
    0.09
    åįĥä¸ĩ
    0.08
    è¢ľ
    0.08
    Activations Density 0.071%

    No Known Activations