© 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. 58533
    Prev
    Next
    INDEX
    Explanations

    light, illumination, lit

    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
    erial
    -0.08
    累累
    -0.07
    念
    -0.07
    unti
    -0.07
    ä¹ĭå¿ĥ
    -0.06
    åĺ´
    -0.06
    è¿ŀçݯ
    -0.06
    å½¢çļĦ
    -0.06
    å¥ij
    -0.06
    åįłåľ°
    -0.06
    POSITIVE LOGITS
    çħ§æĺİ
    0.17
     illumination
    0.16
    çħ§äº®
    0.15
    åħīæºIJ
    0.15
    åħī线
    0.15
     illumin
    0.14
     lighting
    0.14
    สวà¹Īาà¸ĩ
    0.14
    light
    0.13
    çħ§å°Ħ
    0.13
    Activations Density 0.121%

    No Known Activations