© 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. 56425
    Prev
    Next
    INDEX
    Explanations

    made or make something

    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
     COPYRIGHT
    -0.09
    æĭ¨
    -0.09
     Slug
    -0.09
    çıįçıł
    -0.09
    éħ¬
    -0.08
    æĶ¾åģĩ
    -0.08
    .parsers
    -0.08
    çŁ¥æĥħ
    -0.08
    åĥı
    -0.08
     kos
    -0.08
    POSITIVE LOGITS
    欧å¼ı
    0.10
    æį
    0.09
    没å¿ħè¦ģ
    0.09
    xon
    0.09
    fully
    0.09
    éĿĻçĶµ
    0.08
     ÙħÙĨت
    0.08
    çĥŁåĽ±
    0.08
    udu
    0.08
    ç²ī
    0.08
    Activations Density 0.055%

    No Known Activations