© 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. 63869
    Prev
    Next
    INDEX
    Explanations

    as

    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
    ondo
    -0.09
    ToObject
    -0.09
    Ral
    -0.09
    èIJ½
    -0.08
    éļħ
    -0.08
    .raise
    -0.08
    ulators
    -0.08
    Mor
    -0.08
     Hodg
    -0.08
    亡
    -0.08
    POSITIVE LOGITS
    纤
    0.09
    æķ°æį®åĪĨæŀIJ
    0.09
     as
    0.08
    éĩįä¸Ń
    0.08
    æĬ½åĩº
    0.08
    粪
    0.08
    KeyValue
    0.08
     nhất
    0.08
    ç¼Ŀ
    0.08
     quanto
    0.08
    Activations Density 0.068%

    No Known Activations