© 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. 680
    Prev
    Next
    INDEX
    Explanations

    HBO and Game of Thrones

    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
    ãĤĥ
    -0.10
    iday
    -0.10
    è±ĨæµĨ
    -0.09
    天河
    -0.09
     Kitt
    -0.08
    apult
    -0.08
    tings
    -0.08
    åĩºåľº
    -0.08
    æ¯Ķäºļ
    -0.08
    kits
    -0.08
    POSITIVE LOGITS
    erd
    0.11
     Sachs
    0.09
    untime
    0.08
     reactive
    0.08
    åIJĿ
    0.08
    éĶ²
    0.08
    chied
    0.08
    wnd
    0.08
     fracking
    0.08
    .azure
    0.08
    Activations Density 0.002%

    No Known Activations