© 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. 701
    Prev
    Next
    INDEX
    Explanations

    pre-existing

    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
    gor
    -0.09
    proxy
    -0.09
    arb
    -0.09
    orio
    -0.09
     Priv
    -0.09
    æĪIJ为ä¸Ģ个
    -0.09
    åİĤ
    -0.09
    èĥ¸åīį
    -0.09
    æł¹æľ¬æ²¡æľī
    -0.09
    anian
    -0.08
    POSITIVE LOGITS
    楼ä¸ĭ
    0.10
    æ¯ĵ
    0.10
    enko
    0.09
    éĺħè§Ī
    0.09
    å·´æĭī
    0.09
    ä¸Ģç»ı
    0.09
     Exped
    0.09
    dı
    0.08
    __).
    0.08
    íݸ
    0.08
    Activations Density 0.004%

    No Known Activations