© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 11638
    Prev
    Next
    INDEX
    Explanations

    store staff and customers

    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
    éħĴåºĹ
    -0.11
    顶
    -0.09
    hotel
    -0.09
    (mu
    -0.08
     Hotels
    -0.08
    usercontent
    -0.08
     toll
    -0.08
     hotel
    -0.08
    æĪª
    -0.08
     cov
    -0.08
    POSITIVE LOGITS
    åºĹåĨħ
    0.12
    èĢIJå¿ĥ
    0.10
     staff
    0.10
    åľ¨èģĮ
    0.10
    åºĹéĩĮ
    0.10
    å¢Ļå£ģ
    0.09
    顾客
    0.09
    æµľ
    0.09
    éĴĬ
    0.09
    ä¼ĺè¶Ĭ
    0.09
    Activations Density 0.117%

    No Known Activations