© 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. 9421
    Prev
    Next
    INDEX
    Explanations

    greenhouse gas emissions

    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
    utex
    -0.08
    rxjs
    -0.08
    æ´
    -0.07
    entak
    -0.07
    usan
    -0.07
    é²ľè¡Ģ
    -0.07
     sang
    -0.07
    [section
    -0.07
    oust
    -0.07
     scalp
    -0.07
    POSITIVE LOGITS
     warming
    0.12
     IPCC
    0.09
    æķĪåºĶ
    0.09
    温室
    0.09
     warmer
    0.09
     greenhouse
    0.08
    ä¼łå¯¼
    0.08
    温室æ°Ķä½ĵ
    0.08
    åıįå°Ħ
    0.08
    åıĺæļĸ
    0.08
    Activations Density 0.009%

    No Known Activations