© 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. 1869
    Prev
    Next
    INDEX
    Explanations

    relative clauses or phrases

    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
    饶
    -0.12
    称ä¹ĭ
    -0.10
    为åħ¶
    -0.10
    åģļ个
    -0.10
    å·²äºİ
    -0.10
    èĿ¼
    -0.10
    ä¹ŁæĽ¾
    -0.09
    称ä¹ĭ为
    -0.09
    åIJŀ
    -0.09
    åij¼
    -0.09
    POSITIVE LOGITS
    ä¸Ģæĸ¹
    0.09
    äºĭåIJİ
    0.09
    å°±æĺ¯åľ¨
    0.08
    hap
    0.08
    ä»Ģä¹ĪæĦıæĢĿ
    0.08
    åŀĴ
    0.08
    çļĦå°±æĺ¯
    0.08
    aldi
    0.07
     departing
    0.07
     Ferd
    0.07
    Activations Density 0.404%

    No Known Activations