© 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. 663
    Prev
    Next
    INDEX
    Explanations

    milk or dairy products

    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
    ential
    -0.11
    allis
    -0.09
    èªł
    -0.09
    ä¸ļä½Ļ
    -0.09
    åIJĪæł¼
    -0.09
    湫
    -0.08
    dden
    -0.08
    ression
    -0.08
    [state
    -0.08
     hÃłnh
    -0.08
    POSITIVE LOGITS
    çīĽå¥¶
    0.12
    éħª
    0.12
    çĬĬ
    0.11
    ä¹³
    0.10
     Dairy
    0.10
    奶
    0.10
    ç¾Ķ
    0.10
     dairy
    0.10
    ðŁ¥Ľ
    0.10
     Milk
    0.10
    Activations Density 0.076%

    No Known Activations