© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 38424
    Prev
    Next
    INDEX
    Explanations

    country, national, culture

    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
    inux
    -0.10
    æĹ¥åĨħ
    -0.09
    åIJĦåĽ½
    -0.09
    è¡į
    -0.08
    ä¹IJåĽŃ
    -0.08
     اÙĦÙħج
    -0.08
    ippo
    -0.08
    å¤į
    -0.08
    bear
    -0.08
    åĪ©å¥½
    -0.08
    POSITIVE LOGITS
    åĽ½æĥħ
    0.14
    ç¾İåĽ½äºº
    0.13
     Americans
    0.12
     America
    0.12
    åħ¨æ°ij
    0.12
     national
    0.12
    æ°ijä¼Ĺ
    0.11
    åľ¨åħ¨åĽ½
    0.11
     nationwide
    0.11
     American
    0.11
    Activations Density 0.208%

    No Known Activations