© 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. 47460
    Prev
    Next
    INDEX
    Explanations

    every [word]

    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
    天天
    -0.09
    åIJĦèĩªçļĦ
    -0.09
     fellows
    -0.08
    åIJĬ
    -0.08
    ivid
    -0.08
    gether
    -0.08
     geli
    -0.08
    ifers
    -0.08
     choses
    -0.08
    ¯¯¯¯
    -0.08
    POSITIVE LOGITS
    THING
    0.14
    thin
    0.13
    大大å°ıå°ı
    0.11
    ting
    0.11
    ones
    0.11
    人éĥ½
    0.10
    uded
    0.10
    iance
    0.10
    å¹´é¾Ħ段
    0.10
    eer
    0.10
    Activations Density 0.027%

    No Known Activations