© 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. 63511
    Prev
    Next
    INDEX
    Explanations

    characteristics of year/sector/week/function

    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
    éĢļ讯åijĺ
    -0.08
    并ä¸Ķ
    -0.08
    侯
    -0.08
    身边çļĦ
    -0.08
    æ²¼
    -0.08
    _prices
    -0.08
    _LAYOUT
    -0.08
    CurrentValue
    -0.07
    æķ¬è¯·
    -0.07
    ä½ĵä¼ļ
    -0.07
    POSITIVE LOGITS
    æĥħåĨµ
    0.10
     safest
    0.10
    åºı
    0.09
    (#)
    0.09
    ç²Ĺ
    0.08
    Ñĩи
    0.08
    æľĢãĤĤ
    0.08
    å¤ĩ注
    0.08
    tog
    0.08
    еÑĩа
    0.08
    Activations Density 0.216%

    No Known Activations