© 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. 20243
    Prev
    Next
    INDEX
    Explanations

    senior job titles

    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
    ilst
    -0.08
     дол
    -0.08
    ROC
    -0.08
    åĨį度
    -0.08
    ä¸ŃæľŁ
    -0.07
    潦
    -0.07
    æĩĴ
    -0.07
    ç²¢
    -0.07
    é¢ī
    -0.07
    FE
    -0.07
    POSITIVE LOGITS
    åįı
    0.11
    æĭ¥æĮ¤
    0.10
    inand
    0.10
    ä¿Ŀå®ī
    0.10
    å«
    0.10
    upro
    0.09
    çĭİ
    0.09
    åŀ¸
    0.09
    路桥
    0.09
    æĬĺåıł
    0.09
    Activations Density 0.020%

    No Known Activations