© 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. 27421
    Prev
    Next
    INDEX
    Explanations

    markdown editor content

    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
    缸åħ³èµĦ讯
    -0.06
    æĵįä½ľä¸Ĭ
    -0.06
    quan
    -0.06
    ç½ijåıĭè¯Ħ论
    -0.06
    sett
    -0.06
     immigration
    -0.06
     listing
    -0.06
    è£ħ饰设计
    -0.06
    imson
    -0.06
     Nama
    -0.06
    POSITIVE LOGITS
    æĸĩä½ĵ
    0.12
     Markdown
    0.11
     content
    0.10
     text
    0.10
     markdown
    0.10
     prose
    0.10
    Markdown
    0.10
    -text
    0.10
    -editor
    0.09
    richText
    0.09
    Activations Density 0.286%

    No Known Activations