© 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. 37197
    Prev
    Next
    INDEX
    Explanations

    buffer module implementations and usage

    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
    WithContext
    -0.09
    ÑĥÑī
    -0.09
    aux
    -0.09
    onor
    -0.08
    inated
    -0.08
    thic
    -0.08
    æĸĩçĮ®
    -0.08
    zie
    -0.08
     Glory
    -0.08
    ãĥ¦ãĥ¼
    -0.08
    POSITIVE LOGITS
    edImage
    0.11
    irth
    0.10
    edReader
    0.10
    æľŁåĨħ
    0.09
    rary
    0.09
    maid
    0.09
    erve
    0.09
    åıŁ
    0.09
    edList
    0.08
    åģ»
    0.08
    Activations Density 0.033%

    No Known Activations