© 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. 9750
    Prev
    Next
    INDEX
    Explanations

    restaurants and food by nationality

    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
    ç®į
    -0.09
    BLEM
    -0.09
    ниÑĨа
    -0.09
    raries
    -0.09
    çľ¼çļ®
    -0.09
    æĮĩåįĹ
    -0.09
    è·ijäºĨ
    -0.09
     Benz
    -0.08
    midt
    -0.08
     Dimit
    -0.08
    POSITIVE LOGITS
    é£İæł¼
    0.10
    -style
    0.10
    _closure
    0.09
    åįİ举
    0.09
    ä¸Ńåħ³
    0.09
    unk
    0.09
    å¹½
    0.09
    çıį
    0.09
    ity
    0.08
    å¼ı
    0.08
    Activations Density 0.023%

    No Known Activations