© 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. 741
    Prev
    Next
    INDEX
    Explanations

    traditional practices

    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
    大äºĭ
    -0.09
    åİŁæĿ¥æĺ¯
    -0.09
    icit
    -0.09
    ãĥĹãĥ©ãĤ¤
    -0.09
    lut
    -0.09
    羣缸
    -0.09
    åŁ
    -0.08
    aces
    -0.08
    è¿©
    -0.08
    eder
    -0.08
    POSITIVE LOGITS
    æĦıä¹īä¸ĬçļĦ
    0.17
    ists
    0.15
    mente
    0.14
    æĦıä¹īä¸Ĭ
    0.14
    ize
    0.13
    ization
    0.13
    izing
    0.13
    izer
    0.13
    idad
    0.12
    ITY
    0.12
    Activations Density 0.031%

    No Known Activations