© 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. 62265
    Prev
    Next
    INDEX
    Explanations

    editorial, editor, and media groups

    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®£ä¼ł
    -0.10
    çĶµè§Ĩåı°
    -0.10
    èİ·èĥľ
    -0.09
    绥
    -0.09
    åĮª
    -0.08
    毳
    -0.08
    涣
    -0.08
    åĸĩåıŃ
    -0.08
    èĩº
    -0.08
    宣æī¬
    -0.08
    POSITIVE LOGITS
    æĸ°çļĦä¸Ģ
    0.10
    åī¯
    0.09
    igli
    0.08
    è°ĥåĬ¨
    0.08
    åĢ¾
    0.08
    å®ŀä¹łçĶŁ
    0.08
    ç²¾
    0.08
     Interactive
    0.08
    MOST
    0.08
    AFX
    0.08
    Activations Density 0.182%

    No Known Activations