© 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. 1156
    Prev
    Next
    INDEX
    Explanations

    kernel module or license

    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
     Distributed
    -0.09
    ä½Ĺ
    -0.09
    owie
    -0.08
    forecast
    -0.08
    åIJİæľŁ
    -0.08
    å¸ĤåĮº
    -0.08
    distributed
    -0.08
    رÙĥØ©
    -0.08
    åħħå®ŀ
    -0.08
    å¸ĥç½®
    -0.08
    POSITIVE LOGITS
     kernel
    0.12
    .kernel
    0.12
    /kernel
    0.12
    Kernel
    0.11
    _kernel
    0.11
    æł©
    0.10
     Kernel
    0.10
    kernel
    0.10
     kernels
    0.10
     KERNEL
    0.10
    Activations Density 0.266%

    No Known Activations