© 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. 24263
    Prev
    Next
    INDEX
    Explanations

    brand new

    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
    åĹŁ
    -0.10
    weise
    -0.09
    æĢ§å¼º
    -0.09
    ifornia
    -0.09
    oub
    -0.09
    ä»Ģä¹ĪæŶåĢĻ
    -0.09
    寡
    -0.09
    .translation
    -0.08
    ivent
    -0.08
    æĽ´å¤ļçļĦæĺ¯
    -0.08
    POSITIVE LOGITS
    å´Ń
    0.08
    çĻ»åľº
    0.08
    elli
    0.08
    ÑĤе
    0.08
    tte
    0.08
    à¸ļรร
    0.08
    大äºĭ
    0.08
     conco
    0.08
     dipl
    0.08
    ä½Ī
    0.08
    Activations Density 0.010%

    No Known Activations