© 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. 19295
    Prev
    Next
    INDEX
    Explanations

    The [Proper Noun]

    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
    ses
    -0.09
    å·Ŀ
    -0.09
    responsive
    -0.08
    (in
    -0.08
    驾车
    -0.08
    keh
    -0.08
    粤
    -0.08
    声
    -0.08
    ä¸ĩæĪ·
    -0.08
    诸
    -0.07
    POSITIVE LOGITS
    èĬĹ
    0.10
    rys
    0.09
    oretical
    0.09
    agnitude
    0.09
    quets
    0.08
    _TUN
    0.08
    orem
    0.08
    碴
    0.08
    crow
    0.08
     uncon
    0.08
    Activations Density 0.106%

    No Known Activations