© 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. 42044
    Prev
    Next
    INDEX
    Explanations

    force and 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
    æ°´éĩı
    -0.07
    azer
    -0.07
    æ¡Īåıij
    -0.07
     sobres
    -0.07
    æĺ¯æīĢæľī
    -0.06
    ger
    -0.06
    水泡
    -0.06
    دÙħ
    -0.06
     number
    -0.06
     bơi
    -0.06
    POSITIVE LOGITS
     pressures
    0.08
    stress
    0.08
     exert
    0.08
    æĸ½åĬł
    0.08
     stresses
    0.08
    resse
    0.08
    åIJĪåĬĽ
    0.08
     pressure
    0.08
    åºĶåĬĽ
    0.08
     resisting
    0.08
    Activations Density 0.005%

    No Known Activations