© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 59868
    Prev
    Next
    INDEX
    Explanations

    pressure sensor

    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
    Negative Logits
    éķ¿åº¦çļĦ
    -0.08
    è¶Ĭéķ¿
    -0.08
    éķ¿æĪIJ
    -0.08
     Length
    -0.08
    Length
    -0.07
    length
    -0.07
     lengths
    -0.07
    éķ¿åº¦
    -0.07
    éķ¿ç¯ĩ
    -0.07
     length
    -0.07
    POSITIVE LOGITS
     pressure
    0.15
     pressures
    0.14
    -pressure
    0.14
    pressure
    0.14
    åİĭåĬĽ
    0.13
     Pressure
    0.13
    Pressure
    0.12
    åİĭåĬĽçļĦ
    0.12
    çļĦåİĭåĬĽ
    0.11
    è´Łåİĭ
    0.10
    Activations Density 0.012%

    No Known Activations