© 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. 37198
    Prev
    Next
    INDEX
    Explanations

    image and perception

    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
    åĩ»
    -0.10
    é¢ĨæĤŁ
    -0.09
    è¡¢
    -0.08
    ned
    -0.08
     padd
    -0.08
    4
    -0.08
    é¢Ĩä¼ļ
    -0.08
    9
    -0.08
    pedia
    -0.08
    0
    -0.08
    POSITIVE LOGITS
    形象
    0.20
    çļĦ形象
    0.20
    åĵģçīĮ形象
    0.17
    èī¯å¥½
    0.12
     image
    0.12
    çļĦåį°è±¡
    0.12
    'image
    0.12
    /image
    0.11
    image
    0.11
     reputation
    0.11
    Activations Density 0.054%

    No Known Activations