© 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. 6184
    Prev
    Next
    INDEX
    Explanations

    context

    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
    enn
    -0.09
    licht
    -0.09
    quee
    -0.08
    åĿıäºĭ
    -0.08
    /her
    -0.08
     siden
    -0.08
    æĦıå¤ĸ
    -0.08
    hot
    -0.08
    /umd
    -0.08
    æīģ
    -0.08
    POSITIVE LOGITS
    ivism
    0.10
    æļĦ
    0.10
    ively
    0.10
    ual
    0.09
    èĢĮæĿ¥
    0.09
    çīł
    0.09
    å·¥ä½ľèĢħ
    0.09
    社ä¼ļå®ŀè·µ
    0.09
    onical
    0.09
    èĥĦ
    0.09
    Activations Density 0.027%

    No Known Activations