© 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. 5532
    Prev
    Next
    INDEX
    Explanations

    countries and their locations

    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
    åIJijå¾Ģ
    -0.10
    elen
    -0.09
    alam
    -0.09
    intage
    -0.09
    æ°´ä¸Ĭ
    -0.09
     Ara
    -0.09
    æĿijæ°ij们
    -0.09
    é³Ł
    -0.09
    å¼¯æĽ²
    -0.09
     Sas
    -0.09
    POSITIVE LOGITS
    åįļçī©
    0.10
    ainty
    0.08
    çıį
    0.08
    å¢ĥåĨħ
    0.08
    ä¸Ĭåįĩ
    0.08
     osob
    0.08
    åħ¬çĶ¨
    0.07
    ç«ĭãģ¡
    0.07
    éĥ¨åĪĨåľ°åĮº
    0.07
     taper
    0.07
    Activations Density 0.270%

    No Known Activations