© 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. 16532
    Prev
    Next
    INDEX
    Explanations

    recession or recess

    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
    mith
    -0.10
    ings
    -0.10
    å°Ķæĸ¯
    -0.10
    wart
    -0.10
    åįī
    -0.09
    inston
    -0.09
     Hurt
    -0.09
     Contributor
    -0.09
    ç»ĩ
    -0.09
    .presentation
    -0.08
    POSITIVE LOGITS
    ary
    0.13
    naire
    0.11
    ا
    0.10
    éĻĽ
    0.10
    aire
    0.09
    оÑĢа
    0.09
    è¯Ŀ说
    0.09
    ional
    0.09
    è´«è¡Ģ
    0.09
     Got
    0.09
    Activations Density 0.005%

    No Known Activations