© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 57588
    Prev
    Next
    INDEX
    Explanations

    Singh names

    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
    Not in Any Lists

    No Comments

    Negative Logits
    å¯Įæľī
    -0.08
    室å¤ĸ
    -0.08
    æ³Ħ
    -0.08
    ä¸įèĥ½åĨį
    -0.08
    çľł
    -0.08
    æ¦Ķ
    -0.08
    çIJĨæĥ³çļĦ
    -0.08
     impro
    -0.08
    çłĶåĪ¤
    -0.08
    å¹
    -0.08
    POSITIVE LOGITS
     Singh
    0.10
    ä¸įä½ı
    0.09
    nek
    0.09
     Canter
    0.09
    bas
    0.09
    éħ¬
    0.08
     dik
    0.08
    彩票
    0.08
    åĩ¡
    0.08
    ëijIJ
    0.08
    Activations Density 0.061%

    No Known Activations