© 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. 35568
    Prev
    Next
    INDEX
    Explanations

    Thailand and Thai contexts

    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
    nda
    -0.10
    ally
    -0.10
    eer
    -0.09
    èµ³
    -0.08
     Spy
    -0.08
    aires
    -0.08
    nero
    -0.08
    æ²®
    -0.08
    jsc
    -0.08
    åµĬ
    -0.08
    POSITIVE LOGITS
    åºľ
    0.11
     Warwick
    0.10
    -Russian
    0.10
    iei
    0.09
     Bangkok
    0.09
    æĪij们å¿ħé¡»
    0.09
    佬
    0.09
    è¿Ļä¸ªåľ°æĸ¹
    0.09
    arat
    0.09
    ragon
    0.09
    Activations Density 0.015%

    No Known Activations