© 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. 50222
    Prev
    Next
    INDEX
    Explanations

    Tunisia and Algeria

    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
    èĭį
    -0.10
     кап
    -0.09
    æĸ°é²ľ
    -0.09
    çıĪ
    -0.08
     سعÙĪد
    -0.08
     jente
    -0.08
    .getChild
    -0.08
    交äºĴ
    -0.08
    éĦ¢
    -0.08
    HTTPRequest
    -0.08
    POSITIVE LOGITS
    oui
    0.09
    åħ±åĴĮ
    0.09
    æĹ©æĻļ
    0.08
    ibo
    0.08
    lass
    0.08
    åŁºæľ¬ä¿¡æģ¯
    0.08
    çļĦåĬ¨ä½ľ
    0.08
     chain
    0.08
    ivo
    0.08
    æ´¼
    0.08
    Activations Density 0.031%

    No Known Activations