© 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. 52115
    Prev
    Next
    INDEX
    Explanations

    shopping and malls

    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
    Desk
    -0.11
    desk
    -0.10
    æ¯ı天
    -0.10
    .Raise
    -0.09
    наÑĤ
    -0.09
    åĴĢ
    -0.09
    èı°
    -0.09
    沧
    -0.09
    赫
    -0.09
    ä¸įè¦ģ太
    -0.08
    POSITIVE LOGITS
    è´Ńçī©
    0.18
     malls
    0.16
     shopping
    0.15
    éĢĽè¡Ĺ
    0.15
     Shopping
    0.15
     mall
    0.14
    è³¼çī©
    0.14
    éĢĽ
    0.13
    -shopping
    0.12
    shopping
    0.12
    Activations Density 0.102%

    No Known Activations