© 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. 26170
    Prev
    Next
    INDEX
    Explanations

    Kirby

    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
    ãĤıãĤĬ
    -0.11
    å¤ł
    -0.10
    主ä¹īæĢĿæĥ³
    -0.09
    iton
    -0.09
     serialVersionUID
    -0.09
    .SIZE
    -0.09
    eds
    -0.08
    åĭĥåĭĥ
    -0.08
    ç«Ļéķ¿
    -0.08
    oli
    -0.08
    POSITIVE LOGITS
    inear
    0.10
    maid
    0.10
    otle
    0.10
    antha
    0.10
    enef
    0.09
    matic
    0.09
    oen
    0.09
    sey
    0.08
    aise
    0.08
    ç§įç§į
    0.08
    Activations Density 0.017%

    No Known Activations