© 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. 53954
    Prev
    Next
    INDEX
    Explanations

    legislative sessions and sittings

    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
    å²ļ
    -0.10
    èģĮä¸ļçĶŁæ¶¯
    -0.10
    å¸
    -0.10
    fest
    -0.09
    ä¼¢
    -0.09
    åħ¬è®¤çļĦ
    -0.09
    åĵį
    -0.09
    å©ļåIJİ
    -0.09
    ITE
    -0.08
    æĿ¯
    -0.08
    POSITIVE LOGITS
    ä¸ľè¥¿
    0.10
    çķª
    0.09
    éĵĦ
    0.08
    éķ¢
    0.08
    è¡®
    0.08
    èĻ¢
    0.08
     session
    0.08
    ä¸įå®ļ
    0.08
    akra
    0.08
    漫
    0.08
    Activations Density 0.050%

    No Known Activations