© 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. 7310
    Prev
    Next
    INDEX
    Explanations

    tourism and hospitality

    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
    truck
    -0.10
    åĹŁ
    -0.10
    æĶ¯åĩº
    -0.10
    ioc
    -0.09
    æĻºèĥ½åĪ¶éĢł
    -0.09
    大è±Ĩ
    -0.08
    ãĥıãĤ¦ãĤ¹
    -0.08
    åľ°éĵģ
    -0.08
    wich
    -0.08
    æ·ĭ
    -0.08
    POSITIVE LOGITS
    æĹħ游
    0.19
    æĹħ游èµĦæºIJ
    0.18
    æĹħ游ä¸ļ
    0.17
     tourism
    0.17
     tourist
    0.17
     Tourism
    0.16
     ÑĤÑĥÑĢиÑģÑĤ
    0.16
    导游
    0.14
    æĸĩåĮĸæĹħ游
    0.14
    æĹħ游å±Ģ
    0.14
    Activations Density 0.110%

    No Known Activations