© 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. 51961
    Prev
    Next
    INDEX
    Explanations

    run or running actions

    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
    /from
    -0.10
    ately
    -0.10
    ities
    -0.09
    rees
    -0.09
    ãĥĮ
    -0.09
    éĢħ
    -0.09
    ensi
    -0.09
    éļħ
    -0.09
    -Russian
    -0.09
    驾
    -0.09
    POSITIVE LOGITS
    .InteropServices
    0.12
    estone
    0.11
    nable
    0.11
    nings
    0.11
    ¿
    0.11
    leigh
    0.11
    åĴĮå®ĮåĸĦ
    0.10
    away
    0.10
    aways
    0.10
    backs
    0.10
    Activations Density 0.086%

    No Known Activations