© 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. 47747
    Prev
    Next
    INDEX
    Explanations

    daytime, time, lapse

    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
    sWith
    -0.10
    髯
    -0.10
    ãģ³
    -0.10
    и
    -0.09
    æĢ§å¼º
    -0.09
    壮大
    -0.09
    set
    -0.09
    l
    -0.09
    shaw
    -0.08
    ings
    -0.08
    POSITIVE LOGITS
    æĸ¼æĺ¯
    0.10
    oral
    0.09
     вÑģего
    0.09
    è¿Ļæĺ¯æĪij们
    0.09
    loy
    0.09
    cooked
    0.09
    imals
    0.09
    ä¾Ķ
    0.09
    .Pow
    0.09
    æĭĬ
    0.08
    Activations Density 0.002%

    No Known Activations