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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 37006
    Prev
    Next
    INDEX
    Explanations

    definition of "is"

    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
    ENTRY
    -0.09
     ë§ŀ
    -0.08
    å¼ķæĵİ
    -0.08
    piÄĻ
    -0.08
    åŃº
    -0.08
    ged
    -0.08
    åı°ä¸Ĭ
    -0.08
    tron
    -0.08
    ilty
    -0.08
     Rah
    -0.08
    POSITIVE LOGITS
    为æĬĵ
    0.09
     Kitchen
    0.09
    edata
    0.08
    çķĭ
    0.08
     vic
    0.08
    .pan
    0.08
    èģĶ缣
    0.08
    ä¸Ģç«Ļ
    0.08
     applic
    0.08
    åŃIJå¼¹
    0.08
    Activations Density 0.025%

    No Known Activations