© 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. 57052
    Prev
    Next
    INDEX
    Explanations

    foreign country names/references

    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
    æĸ¯åŁº
    -0.09
    ä½łçŁ¥éģĵ
    -0.09
    Advertisements
    -0.09
    edBy
    -0.09
    è¸ıå®ŀ
    -0.08
    æݥ纳
    -0.08
    æIJ½
    -0.08
    thin
    -0.08
    ï¸ı
    -0.08
     caus
    -0.08
    POSITIVE LOGITS
    unnel
    0.10
     Zak
    0.09
    adel
    0.09
    ä»Ĺ
    0.09
    ÑĢÑĭ
    0.09
     Zam
    0.09
    åŀ¸
    0.09
    war
    0.09
    cape
    0.09
    à®±
    0.08
    Activations Density 0.006%

    No Known Activations