© 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. 8505
    Prev
    Next
    INDEX
    Explanations

    applied load or stress

    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
    æĽ´æĸ°æŶéĹ´
    -0.08
    ä¹ĭçªĹ
    -0.07
    arus
    -0.07
    æĬķèµĦæľºä¼ļ
    -0.07
    òi
    -0.07
    "default
    -0.07
    åı¯åĶ®
    -0.07
    วย
    -0.07
    大åĪĢ
    -0.07
    ikian
    -0.07
    POSITIVE LOGITS
    æĸ½åĬł
    0.10
     stress
    0.10
     stresses
    0.10
    -induced
    0.10
     stressing
    0.10
    éĩıåĬĽ
    0.09
    stress
    0.09
     induce
    0.09
     induces
    0.09
     applied
    0.08
    Activations Density 0.091%

    No Known Activations