© 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. 6071
    Prev
    Next
    INDEX
    Explanations

    with a/an/the

    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
    edm
    -0.12
    åĮĸè¿Ľç¨ĭ
    -0.10
    åĪĹåħ¥
    -0.09
    Advertisements
    -0.09
    æĮĿ
    -0.08
    fans
    -0.08
     boca
    -0.08
    ×ķ׳×Ķ
    -0.08
    åĿļæĮģ以
    -0.08
    çŁ¥éģĵäºĨ
    -0.08
    POSITIVE LOGITS
    主æĦı
    0.11
    æĸ°çļĦ
    0.10
    äºĨä¸Ģåı¥
    0.09
    çŃĸ
    0.09
    ä¸Ģ个éĹ®é¢ĺ
    0.09
    äºĨä¸ĢäºĽ
    0.09
    er
    0.09
     excuses
    0.09
    ExecutionContext
    0.09
    对çŃĸ
    0.09
    Activations Density 0.012%

    No Known Activations