© 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. 60799
    Prev
    Next
    INDEX
    Explanations

    ages, levels, grades

    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
    enta
    -0.08
    ä¸į符åIJĪ
    -0.08
    WithContext
    -0.07
    çŀ½
    -0.07
    åľ¨çĶŁæ´»ä¸Ń
    -0.07
     cling
    -0.07
    Stride
    -0.07
    ãĤ·
    -0.07
    æĪIJ为ä¸Ģ个
    -0.07
     tart
    -0.07
    POSITIVE LOGITS
    åĵ²
    0.10
    åĭ¿
    0.10
    .Sdk
    0.10
    AGES
    0.10
    ä¸įå®ľ
    0.09
    åIJijãģij
    0.09
    润
    0.09
    èĥ«
    0.09
    çĿ¡åīį
    0.09
    泺
    0.09
    Activations Density 0.039%

    No Known Activations