© 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. 18412
    Prev
    Next
    INDEX
    Explanations

    hydraulic actuation systems

    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
    交çĶµ
    -0.08
     Radiation
    -0.08
     antenn
    -0.07
    ä¸´æ±Ł
    -0.07
     compiler
    -0.07
    æĻ¶ç¡ħ
    -0.07
    秦å§ĭçļĩ
    -0.07
    çĶµä»·
    -0.07
    Detector
    -0.06
     Tonight
    -0.06
    POSITIVE LOGITS
    液åİĭæ²¹
    0.13
    液åİĭ
    0.13
     hydraul
    0.12
     pressure
    0.12
     hydraulic
    0.12
    å·¥ä½ľåİĭåĬĽ
    0.12
    -pressure
    0.11
     Hydraulic
    0.11
    pressure
    0.11
    Pressure
    0.11
    Activations Density 0.075%

    No Known Activations