© 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. 52002
    Prev
    Next
    INDEX
    Explanations

    international policy and geopolitical studies

    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
    _LR
    -0.09
     hurd
    -0.09
    ç©¿æĪ´
    -0.09
    åIJįä¹ī
    -0.08
    以人为
    -0.08
    RowCount
    -0.08
    è·ij
    -0.08
    ç»ıåİĨäºĨ
    -0.08
    æİ¥åΰ
    -0.08
    泸
    -0.08
    POSITIVE LOGITS
    å¤ĸ交
    0.11
    åĽ½éĺ²
    0.11
    ä¸Ń举
    0.10
    foreign
    0.09
    åĽ½å®ī
    0.09
    ãĥªãĤ¢
    0.09
    xit
    0.09
     sh
    0.09
    fort
    0.08
     bury
    0.08
    Activations Density 0.141%

    No Known Activations