© 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. 32411
    Prev
    Next
    INDEX
    Explanations

    electrical protection and fuses

    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
    FetchRequest
    -0.09
    èĭ¦æģ¼
    -0.08
    furt
    -0.08
    caria
    -0.08
    足迹
    -0.07
    êt
    -0.07
    Fetcher
    -0.07
    åªĴ
    -0.07
    æĿĤ
    -0.07
    icole
    -0.07
    POSITIVE LOGITS
     protection
    0.12
    ä¿ĿæĬ¤
    0.11
     safeguard
    0.10
     protecting
    0.10
     protect
    0.10
    ä¿ĿæĬ¤è£ħç½®
    0.10
     protects
    0.10
     protective
    0.10
     safeguards
    0.10
    çĨĶæĸŃ
    0.10
    Activations Density 0.039%

    No Known Activations