© 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. 24246
    Prev
    Next
    INDEX
    Explanations

    tray or pallet

    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
    ariat
    -0.09
    åľ¨ä»Ĭå¹´
    -0.09
    appropri
    -0.09
    ext
    -0.09
    vation
    -0.08
     Brent
    -0.08
    _tunnel
    -0.08
    íģ¼
    -0.08
    oblin
    -0.08
    .getLine
    -0.08
    POSITIVE LOGITS
    ettes
    0.10
    ster
    0.09
    ette
    0.08
    istor
    0.08
    åŁİå¸Ĥ群
    0.08
    lots
    0.08
    溢
    0.08
    lot
    0.08
    ed
    0.08
    åĬŀ好
    0.08
    Activations Density 0.010%

    No Known Activations