© 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. 35888
    Prev
    Next
    INDEX
    Explanations

    Republicans oppose legislation

    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
    æĪIJ为ä¸ĢåIJį
    -0.12
    æł¡éķ¿
    -0.12
    äºĨä»ĸçļĦ
    -0.11
    çķ¿
    -0.11
    个人
    -0.11
    个人è§ĤçĤ¹
    -0.11
    ippy
    -0.11
     personally
    -0.10
    åĴĮä»ĸçļĦ
    -0.10
    -gap
    -0.10
    POSITIVE LOGITS
     themselves
    0.14
    ä¸Ģèĩ´
    0.09
    åIJĦèĩª
    0.09
     Ñģами
    0.09
    åĨįä¸Ģ次
    0.08
    åĽĽä½į
    0.08
    ional
    0.08
    对çŃĸ
    0.08
     cohesion
    0.08
    ally
    0.08
    Activations Density 0.071%

    No Known Activations