© 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. 59180
    Prev
    Next
    INDEX
    Explanations

    food consumption

    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
    Negative Logits
    éĽĨä¸Ńåľ¨
    -0.09
     paraph
    -0.09
    5
    -0.09
    3
    -0.08
    ilm
    -0.08
    1
    -0.08
    icus
    -0.08
    2
    -0.08
    4
    -0.08
    ioc
    -0.08
    POSITIVE LOGITS
    ä½ľä¸ºä¸Ģç§į
    0.12
    _logic
    0.10
    æĺ¯ä¸Ģç§į
    0.09
    å±ŀ
    0.09
    天天
    0.09
    æīĢæıIJä¾Ľ
    0.09
    emed
    0.09
    ett
    0.09
     med
    0.09
    _RAM
    0.09
    Activations Density 0.113%

    No Known Activations