© 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. 5266
    Prev
    Next
    INDEX
    Explanations

    legislative bodies or government representatives

    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
    ç§ģ人
    -0.10
    åģļ人
    -0.09
    CHED
    -0.09
    èķī
    -0.09
    ç±į
    -0.09
    å¥
    -0.09
    æīİå®ŀ
    -0.08
    è§Ħ
    -0.08
    æijĬ
    -0.08
    /helper
    -0.08
    POSITIVE LOGITS
    è®®ä¼ļ
    0.15
     Congress
    0.13
    çIJĨäºĭä¼ļ
    0.12
     parliament
    0.12
     Parliament
    0.11
    åĽ½ä¼ļ
    0.11
     Council
    0.11
     council
    0.11
    Council
    0.11
    à¸ªà¸łà¸²
    0.10
    Activations Density 0.129%

    No Known Activations