© 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. 7989
    Prev
    Next
    INDEX
    Explanations

    attractions

    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
    侦
    -0.10
    å²ĺ
    -0.10
    æ³ķå¾ĭ责任
    -0.09
    æľīå¿ħè¦ģ
    -0.09
    ç¾İå¾·
    -0.08
    éĨª
    -0.08
    abad
    -0.08
    親
    -0.08
    MMC
    -0.08
    croll
    -0.08
    POSITIVE LOGITS
    DataExchange
    0.10
    ุม
    0.09
    人士
    0.09
    æijĬ
    0.09
    adio
    0.08
    rss
    0.08
     arguably
    0.08
     Attr
    0.08
    åIJ¸å¼ķåĬĽ
    0.08
    лин
    0.08
    Activations Density 0.006%

    No Known Activations