© 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. 604
    Prev
    Next
    INDEX
    Explanations

    returning, coming back, or moving on

    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
    åĿ¯
    -0.10
    cem
    -0.08
    Mono
    -0.08
    顺
    -0.08
    foon
    -0.08
    rov
    -0.08
    è°¤
    -0.08
    èݳ
    -0.08
    èļ¯
    -0.08
    åĤį
    -0.08
    POSITIVE LOGITS
    带æĿ¥
    0.10
    åıĪä¸Ģ次
    0.09
    çİ°åĩº
    0.09
    åĬ¨æīĭ
    0.08
    æľī个
    0.08
    åıªçŁ¥éģĵ
    0.08
    ä¸ĢèĤ¡
    0.08
    åħ¨æĸ°
    0.08
    è¶Ĭ大
    0.08
    èĢĮæĿ¥
    0.08
    Activations Density 0.189%

    No Known Activations