© 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. 29624
    Prev
    Next
    INDEX
    Explanations

    spa and medical treatments

    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
    yr
    -0.09
    itz
    -0.09
    .Pool
    -0.08
    Marks
    -0.08
    ç»ĥ
    -0.08
    èĩªæķij
    -0.08
    yte
    -0.08
     WAL
    -0.08
     hair
    -0.08
    .Annotations
    -0.08
    POSITIVE LOGITS
    heads
    0.10
    å²ij
    0.09
    .widgets
    0.09
    .binding
    0.09
    åľ¨çİ°åľº
    0.09
    assen
    0.09
    ounty
    0.09
     Ecology
    0.09
    骨
    0.09
    lever
    0.08
    Activations Density 0.009%

    No Known Activations