© 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. 62959
    Prev
    Next
    INDEX
    Explanations

    regional cooperation, climate, or geography

    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
    /umd
    -0.10
    chy
    -0.09
    åģļå®Į
    -0.08
    Middleware
    -0.08
    lamp
    -0.08
    æĪij对
    -0.08
    çĥĪ
    -0.08
    ç¹ĩ
    -0.08
    æĢ»éĥ¨
    -0.08
    å¼ĢéŨ
    -0.07
    POSITIVE LOGITS
    åľ°åĮº
    0.18
     region
    0.18
    åľ°åĮºçļĦ
    0.17
    -region
    0.16
    åij¨åĽ´
    0.14
     area
    0.14
    region
    0.14
    åľ°åįĢ
    0.14
     اÙĦÙħÙĨØ·ÙĤØ©
    0.14
     región
    0.13
    Activations Density 0.126%

    No Known Activations