© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 8429
    Prev
    Next
    INDEX
    Explanations

    Nepal and Nepalese context

    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
    ymi
    -0.10
    eler
    -0.09
    rary
    -0.09
    æ±ľ
    -0.08
    è¾ĸ
    -0.08
    ners
    -0.08
     Shore
    -0.08
    èĢģ人家
    -0.08
    æ¹Ľæ±Ł
    -0.08
    reater
    -0.08
    POSITIVE LOGITS
    åĸĩ
    0.11
    å±±åĮº
    0.11
    çijľ
    0.10
     Nep
    0.10
    ammen
    0.09
    anch
    0.09
    èĸ°
    0.09
    éĺĹ
    0.09
     Nepal
    0.09
    achu
    0.09
    Activations Density 0.010%

    No Known Activations