© 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. 59432
    Prev
    Next
    INDEX
    Explanations

    numbers like 2, 3, 41, 16, 200, 15, 1808, 1806, 9/11

    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
    æŁ¢
    -0.09
    éĩįéĩį
    -0.09
    omorphic
    -0.09
    大ä¼Ĺ
    -0.09
    oval
    -0.09
    دا
    -0.09
    AIT
    -0.08
    ľ
    -0.08
    erman
    -0.08
    ted
    -0.08
    POSITIVE LOGITS
    ity
    0.12
    ãĥ³
    0.10
    eses
    0.09
    åľ¨æĪijåĽ½
    0.09
    åľ¨è¿Ļç§į
    0.08
    .Localization
    0.08
    elda
    0.08
    ê¹IJ
    0.08
    ба
    0.08
    egration
    0.08
    Activations Density 0.015%

    No Known Activations