© 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. 63710
    Prev
    Next
    INDEX
    Explanations

    bilateral/international trade and relations

    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
    orate
    -0.09
    glass
    -0.09
    ewood
    -0.08
    责令
    -0.08
    Eigen
    -0.08
    _TM
    -0.08
    è½»
    -0.08
    .Attributes
    -0.08
    ä¸įå±ŀäºİ
    -0.08
    guards
    -0.08
    POSITIVE LOGITS
    交æµģ
    0.19
    æĸĩåĮĸ交æµģ
    0.17
    åıĮæĸ¹
    0.15
    对æĸ¹
    0.15
    åıĮè¾¹
    0.15
    ä¸¤åĽ½
    0.14
    交æµģåIJĪä½ľ
    0.13
    åıĭ好
    0.13
    交æį¢
    0.13
    å°įæĸ¹
    0.13
    Activations Density 0.083%

    No Known Activations