© 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. 23742
    Prev
    Next
    INDEX
    Explanations

    content or body

    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
    ابÙĬ
    -0.07
    estina
    -0.06
    æĮĩæ¨Ļ
    -0.06
    ä¸ºä½łæݨèįIJ
    -0.06
    _defaults
    -0.06
    åįıåĴĮ
    -0.06
    zÄħt
    -0.06
    ξη
    -0.06
    ائÙĬ
    -0.06
     nearest
    -0.06
    POSITIVE LOGITS
     content
    0.14
    content
    0.13
     contents
    0.12
    åĨħ容
    0.12
    åĨħå®¹è¿Ľè¡Į
    0.12
    Content
    0.11
    åĨħ容çļĦ
    0.11
    åħ§å®¹
    0.11
    _content
    0.11
    åĨħ容åĴĮ
    0.11
    Activations Density 0.393%

    No Known Activations