© 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. 40083
    Prev
    Next
    INDEX
    Explanations

    phones and Android devices

    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
    ä¸įåıĬ
    -0.09
    èĬ±èįī
    -0.09
    åī¿
    -0.09
    kest
    -0.09
     Skinner
    -0.09
    _frontend
    -0.09
    æ°Ķæ°Ľ
    -0.09
    aska
    -0.09
    桧
    -0.08
    layui
    -0.08
    POSITIVE LOGITS
     Android
    0.11
    çĶµæ±ł
    0.11
    æĻºèĥ½æīĭæľº
    0.10
    /android
    0.10
    Android
    0.10
     android
    0.09
    çĤĢ
    0.09
     accessory
    0.09
    çłĸ
    0.09
    -cell
    0.09
    Activations Density 0.194%

    No Known Activations