© 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. Qwen3.5-4B
    5. 15-RES-MATRYOSHKA-65K
    7. 17815
    Prev
    Next
    INDEX
    Explanations

    embassy, consulate, diplomatic missions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    decoderesearch/qwen-3.5-saes/qwen-3.5-4b
    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
    rac
    -0.06
    aime
    -0.05
    导轨
    -0.05
     industrial
    -0.05
    éļIJéļIJ
    -0.05
    èģĮæķĻ
    -0.05
    主æĮģä¼ļè®®
    -0.05
    举éĥ¨
    -0.05
    ÙĬرة
    -0.05
     chắc
    -0.05
    POSITIVE LOGITS
    бÑĥдÑĮÑĤе
    0.06
     diplomatic
    0.06
     diplom
    0.06
    åįİåºľ
    0.06
    åİŁä»¶åıĬå¤įåį°ä»¶
    0.06
    äºİ
    0.06
    ersion
    0.06
    irut
    0.06
    sev
    0.05
    å¤ĸ交
    0.05
    Activations Density 0.030%

    No Known Activations