© 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
    2. Qwen3-32B
    3. 32-RESID-BATCHTOPK-65K
    4. 20433
    Prev
    Next
    INDEX
    Explanations

    expansion and growth

    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
    ted
    -0.10
     Exped
    -0.09
    воÑĢ
    -0.09
    umen
    -0.09
    bomb
    -0.09
    lessly
    -0.09
    ä¹į
    -0.08
    iming
    -0.08
    å¼Ģåľº
    -0.08
    hape
    -0.08
    POSITIVE LOGITS
    ible
    0.12
    ulary
    0.10
    /stretch
    0.10
    -minded
    0.10
     rãi
    0.09
    ä¼Ļ
    0.09
    /ref
    0.09
    ILON
    0.09
    äºĨèĩªå·±çļĦ
    0.09
    å¹´å¤ľ
    0.09
    Activations Density 0.027%

    No Known Activations