© 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. 52170
    Prev
    Next
    INDEX
    Explanations

    arrival and departure times

    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
    èĥ¸åīį
    -0.10
    ht
    -0.10
    ä¸ĢåĪĢ
    -0.10
    æ£ļ
    -0.09
    éĹ»åIJį
    -0.09
    ews
    -0.08
    åīª
    -0.08
    åĨĮ
    -0.08
    ometry
    -0.08
    ADVERTISEMENT
    -0.08
    POSITIVE LOGITS
    客人
    0.11
     Airbnb
    0.10
     guests
    0.10
    åĨľå®¶ä¹IJ
    0.10
    度åģĩ
    0.10
     Guests
    0.10
    主人
    0.09
    æ°ij宿
    0.09
    æł¼å±Ģ
    0.09
    guest
    0.09
    Activations Density 0.235%

    No Known Activations