© 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. 53771
    Prev
    Next
    INDEX
    Explanations

    foreign policy and geopolitical events

    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
    .sax
    -0.09
    ainers
    -0.09
    åĪ
    -0.09
    åIJĦ级
    -0.09
    htub
    -0.09
    é¢Ĩ导干éĥ¨
    -0.08
    /lic
    -0.08
    å¹²éĥ¨
    -0.08
    究
    -0.08
    ixer
    -0.08
    POSITIVE LOGITS
    æıĸ
    0.10
    æĸ¹éĿ¢çļĦ
    0.10
    满满çļĦ
    0.10
     оÑĩеÑĢед
    0.10
    çļĦçľ¼åħī
    0.09
    éĢ¡
    0.09
    æīĵä»Ĺ
    0.09
    èµ³
    0.09
    èľ©
    0.08
    amu
    0.08
    Activations Density 0.026%

    No Known Activations