© 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. 2640
    Prev
    Next
    INDEX
    Explanations

    foreign minister or affairs

    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
    èĢĨ
    -0.11
    çĪ¬ä¸Ĭ
    -0.10
     Slee
    -0.09
    顺åĬ¿
    -0.09
    é«ĺä½İ
    -0.09
    åįİ缼
    -0.09
     enforced
    -0.09
    表éĿ¢ä¸Ĭ
    -0.09
    áĢĵ
    -0.09
    ä»ĸä¹Ł
    -0.09
    POSITIVE LOGITS
    å¥ī
    0.12
    æĭĽ
    0.10
     affairs
    0.09
    -facing
    0.08
     Affairs
    0.08
    éĩįåŀĭ
    0.08
    fo
    0.08
    s
    0.08
    most
    0.08
    çĭIJ
    0.08
    Activations Density 0.014%

    No Known Activations