© 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. 6079
    Prev
    Next
    INDEX
    Explanations

    logged in

    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
    äºĨä¸įå°ij
    -0.10
    ä¸įäºĨ
    -0.09
    ç¥ł
    -0.09
    带头
    -0.08
    åĸĿæ°´
    -0.08
     Patton
    -0.08
    羣æĥħ
    -0.08
    agon
    -0.08
    æ¡IJ
    -0.08
    èį»
    -0.08
    POSITIVE LOGITS
    ä¸Ĭä¸ĭ
    0.09
    ä»ĭ
    0.09
    ons
    0.08
    çľĭè¿ĩ
    0.08
    éªħ
    0.08
    gable
    0.08
    ìŀĶ
    0.08
    /Admin
    0.08
    lund
    0.08
    edList
    0.08
    Activations Density 0.013%

    No Known Activations