© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 26404
    Prev
    Next
    INDEX
    Explanations

    Apple products and services

    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
    夹
    -0.09
    大è±Ĩ
    -0.09
    äºĮ线
    -0.09
    çļĦè¡£æľį
    -0.09
    åĸĩåıŃ
    -0.08
    ä¹ĭåĬ¿
    -0.08
    çĥĻ
    -0.08
    ä¹±
    -0.08
    layui
    -0.08
    è±Ĩ
    -0.08
    POSITIVE LOGITS
    .apple
    0.13
     Siri
    0.12
     Apple
    0.11
     iCloud
    0.10
    AppDelegate
    0.10
     iPhone
    0.10
     iTunes
    0.10
    Apple
    0.10
    (iOS
    0.10
     iPhones
    0.10
    Activations Density 1.158%

    No Known Activations