© 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. 8918
    Prev
    Next
    INDEX
    Explanations

    language 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
    以èī²
    -0.11
     trif
    -0.10
     пÑĢеп
    -0.10
    iom
    -0.09
    åѦä¼ļ
    -0.09
    eters
    -0.09
    çĨŁ
    -0.08
    ieg
    -0.08
    åįļä¼ļ
    -0.08
    lov
    -0.08
    POSITIVE LOGITS
     phá
    0.09
    åī¯ä¸»å¸Ń
    0.09
    æĮīä¸ĭ
    0.09
    _CHK
    0.09
     اÙĦÙħر
    0.08
     Ñģли
    0.08
     wipes
    0.08
    _cmds
    0.08
    /Gate
    0.08
    諸
    0.08
    Activations Density 0.123%

    No Known Activations