© 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
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 36673
    Prev
    Next
    INDEX
    Explanations

    treaty-making and participation

    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
    æĭĶ
    -0.10
    åIJĦ家
    -0.09
    æĶ¹èī¯
    -0.09
    atile
    -0.09
    è¿Ļ个èģĮä¸ļ
    -0.09
    åłĻ
    -0.09
    æī¶
    -0.08
    itarian
    -0.08
    sector
    -0.08
    é¢ĺ主
    -0.08
    POSITIVE LOGITS
    åĬłåħ¥
    0.17
    åĬłåħ¥äºĨ
    0.16
    积æŀģåıĤä¸İ
    0.14
    åıĤåĬł
    0.13
    åıĤä¸İ
    0.13
    åıĤåĬłäºĨ
    0.13
     join
    0.12
     participation
    0.12
    Join
    0.11
     Participation
    0.11
    Activations Density 0.049%

    No Known Activations