© 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. 26064
    Prev
    Next
    INDEX
    Explanations

    term 'used to refer'

    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
    ctype
    -0.09
    erland
    -0.08
    itemap
    -0.07
    æĢİä¹ĪåĬŀåij¢
    -0.07
     ctype
    -0.07
     bernama
    -0.07
     priced
    -0.07
    ÙĪغ
    -0.07
    åŃĿæķ¬
    -0.07
    anel
    -0.07
    POSITIVE LOGITS
     synonym
    0.11
     referring
    0.11
     synonymous
    0.10
    è¿Ļ个è¯į
    0.10
     обознаÑĩа
    0.10
    æ³ĽæĮĩ
    0.10
     Ñģино
    0.10
    ä¸Ģè¯į
    0.09
    æīĢæĮĩ
    0.09
     coined
    0.09
    Activations Density 0.169%

    No Known Activations