© 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. 32971
    Prev
    Next
    INDEX
    Explanations

    espionage, regime, and invasion

    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
    _VC
    -0.09
    upert
    -0.08
    Dollar
    -0.08
     czar
    -0.08
    éŃĶ鬼
    -0.08
    èĭ±æĸĩåIJįåŃĹ
    -0.08
    åħĪçĶŁåľ¨
    -0.08
     Gén
    -0.08
    åħ«ä»Ļ
    -0.08
    å°ıæ¡¥
    -0.08
    POSITIVE LOGITS
     humanoid
    0.08
     seperate
    0.08
    ائ
    0.07
     nearby
    0.07
    âĢ¦
    0.07
    ä¸ĵç²¾
    0.07
    âĸĪâĸĪ
    0.07
    å¹³æĹ¥éĩĮ
    0.07
    è®®ä¼ļ
    0.07
     atop
    0.07
    Activations Density 0.499%

    No Known Activations