© 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. 33368
    Prev
    Next
    INDEX
    Explanations

    pressure

    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
    åIJį人
    -0.07
     Laz
    -0.06
    Evt
    -0.06
     üzer
    -0.06
    çľ¼çº¿
    -0.06
    spor
    -0.06
    íķ
    -0.06
    ä¸įåħį
    -0.06
    ordan
    -0.06
    pers
    -0.06
    POSITIVE LOGITS
    Pressure
    0.10
     Pressure
    0.10
     pressure
    0.09
    pressure
    0.09
    åİĭåĬĽçļĦ
    0.09
    åİĭåĬĽ
    0.09
    -pressure
    0.09
    _pressure
    0.08
    èĥĢ
    0.08
     pressures
    0.08
    Activations Density 0.003%

    No Known Activations