© 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. 12415
    Prev
    Next
    INDEX
    Explanations

    burn words

    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
    /from
    -0.11
    ially
    -0.10
    ities
    -0.10
    ively
    -0.09
    ekt
    -0.09
    usk
    -0.09
    ubo
    -0.09
    æĢ§å¼º
    -0.09
    IOS
    -0.09
    ually
    -0.09
    POSITIVE LOGITS
    æ®Ĩ
    0.13
    ished
    0.12
    lö
    0.12
    ers
    0.11
    rie
    0.09
    ingly
    0.09
    ners
    0.09
    é¹ķ
    0.09
    nings
    0.09
    ÙĨظر
    0.09
    Activations Density 0.018%

    No Known Activations