© 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. 57637
    Prev
    Next
    INDEX
    Explanations

    for [legal party]

    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
    é¢Ģ
    -0.10
    æ®·
    -0.10
     Kathleen
    -0.09
    åĽŀæĿ¥
    -0.09
    æĬ¢
    -0.08
    ç´§
    -0.08
    fine
    -0.08
    mania
    -0.08
     pl
    -0.08
     Uncategorized
    -0.08
    POSITIVE LOGITS
    ChangeEvent
    0.11
    еÑĢÑĮ
    0.10
     Libyan
    0.09
    é¼ĵ
    0.09
    igua
    0.09
    igu
    0.09
    æīĺ
    0.09
    ê²½ìĺģ
    0.09
     вÑģÑİ
    0.08
    loi
    0.08
    Activations Density 0.131%

    No Known Activations