© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 6939
    Prev
    Next
    INDEX
    Explanations

    magnitude or brightness

    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
    Negative Logits
    ×Ļצ
    -0.08
    é£İè¡Į
    -0.08
    ovich
    -0.07
    anf
    -0.07
    ÙĪاج
    -0.07
    tale
    -0.07
    管å§Ķä¼ļ
    -0.07
    _CAPACITY
    -0.07
    åįİå°Ķ
    -0.07
    æħ¢è·ij
    -0.07
    POSITIVE LOGITS
    亮度
    0.08
    -rating
    0.08
     brightness
    0.07
    gradable
    0.07
     Chart
    0.07
    æĺ¼
    0.07
     ëĵ±ê¸ī
    0.07
     grade
    0.07
    =-
    0.07
    grade
    0.07
    Activations Density 0.009%

    No Known Activations