© 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. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 16860
    Prev
    Next
    INDEX
    Explanations

    sanctions, boycott, blockade, embargo, strike

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    精讲
    -0.07
    个æķ°
    -0.07
    andles
    -0.07
     ØŃادث
    -0.06
    容纳
    -0.06
    rox
    -0.06
     glimps
    -0.06
    ersey
    -0.06
    ÙIJØŃ
    -0.06
    nict
    -0.06
    POSITIVE LOGITS
     boycott
    0.12
    åĪ¶è£ģ
    0.11
     boyc
    0.11
    æļĤåģľ
    0.10
     withholding
    0.10
    åģľçĶ¨
    0.10
     blockade
    0.09
    å°ģéĶģ
    0.09
     embargo
    0.09
     suspension
    0.09
    Activations Density 0.153%

    No Known Activations