© 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. 1346
    Prev
    Next
    INDEX
    Explanations

    names followed by family or description

    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
    cheng
    -0.09
    igne
    -0.09
    ä¸Ģ带ä¸Ģè·¯
    -0.09
    ogn
    -0.09
    isen
    -0.09
    åĪĩãĤĬ
    -0.08
    åįļä¼ļ
    -0.08
    кÑĢ
    -0.08
    _AUTO
    -0.08
    æĵ
    -0.08
    POSITIVE LOGITS
     веÑĩ
    0.09
    读åIJİ
    0.09
    /OR
    0.08
    ç½Ĥ
    0.08
    é¢Ģ
    0.08
    ãĤĤãģĨ
    0.08
    æĪĸèĢħåħ¶ä»ĸ
    0.08
    说å¾Ĺ
    0.08
    å¯¹æľªæĿ¥
    0.08
    人家
    0.08
    Activations Density 0.062%

    No Known Activations