© 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. 54659
    Prev
    Next
    INDEX
    Explanations

    product line introduction

    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
    é¼ĵ
    -0.10
    andler
    -0.09
    ноп
    -0.09
    æµħ
    -0.08
    pecified
    -0.08
     Swan
    -0.08
    å¢ŀ
    -0.08
    èıħ
    -0.08
    ĶĦ
    -0.08
    phia
    -0.08
    POSITIVE LOGITS
    æĸ°äº§åĵģ
    0.21
    æݨåĩº
    0.19
    产åĵģ
    0.17
    æݨåĩºäºĨ
    0.17
    æݨåĩºçļĦ
    0.16
    产åĵģçļĦ
    0.16
     products
    0.15
    æĸ°åĵģ
    0.15
    ç³»åĪĹ产åĵģ
    0.14
     Products
    0.14
    Activations Density 0.154%

    No Known Activations