© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 37601
    Prev
    Next
    INDEX
    Explanations

    orientalism, Oriental, Eastern

    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
    ros
    -0.08
    èįĴ
    -0.08
    æľ¬ç«Ļ
    -0.08
    elin
    -0.08
    anes
    -0.08
    former
    -0.08
    åı¯æĥ³
    -0.08
    éĥ¢
    -0.08
    apter
    -0.08
    yan
    -0.08
    POSITIVE LOGITS
     Ñģобой
    0.11
    meld
    0.10
    izing
    0.10
    æĹłçŁ¥
    0.10
    IZER
    0.10
    è¾Ĥ
    0.10
    à¹Ħà¸Ĺ
    0.10
    SetValue
    0.09
    IgnoreCase
    0.09
    ogy
    0.09
    Activations Density 0.013%

    No Known Activations