© 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. 52084
    Prev
    Next
    INDEX
    Explanations

    gaines and places ending in ville or bourg

    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
    çªł
    -0.08
    æĻļé¥Ń
    -0.08
    ãĪľ
    -0.08
    ÙħÙĥاÙĨ
    -0.08
    rapper
    -0.08
    ä¸Ģå¼Ģå§ĭå°±
    -0.08
    лег
    -0.07
     днÑı
    -0.07
    Ñıв
    -0.07
    .Fire
    -0.07
    POSITIVE LOGITS
    ä¸ĭè¡Į
    0.09
    èĦĵ
    0.09
    çįł
    0.09
    æľ¬çĶ°
    0.09
    stag
    0.08
    iche
    0.08
    onet
    0.08
    aland
    0.08
    éĩĮçļĦ
    0.08
    à¤Ī
    0.08
    Activations Density 0.002%

    No Known Activations