© 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. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 11563
    Prev
    Next
    INDEX
    Explanations

    faction vs president or peace

    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
    å¹Į
    -0.07
    æļĩ
    -0.07
     eer
    -0.06
     screenings
    -0.06
    çĽ¸ä¼¼çļĦ
    -0.06
    åĢºåĬ¡åĪ©æģ¯
    -0.06
     pii
    -0.06
    à¸ļัà¸ĩ
    -0.06
     searchable
    -0.06
     laps
    -0.06
    POSITIVE LOGITS
    代表çļĦ
    0.12
    åıį对
    0.11
     vs
    0.11
     faction
    0.11
     versus
    0.10
     dominant
    0.10
    代表
    0.10
    ä¸»å¼ł
    0.10
     factions
    0.10
    主导
    0.10
    Activations Density 0.315%

    No Known Activations