© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 20555
    Prev
    Next
    INDEX
    Explanations

    hyperlinks and links

    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
    oise
    -0.08
    羯
    -0.07
    gesteld
    -0.07
     noise
    -0.07
    uan
    -0.07
    ottle
    -0.07
    åİŁåĪĽæĸĩç«ł
    -0.07
    åĻªéŁ³
    -0.07
     óc
    -0.07
    缸åħ³èµĦ讯
    -0.07
    POSITIVE LOGITS
    éĵ¾æİ¥
    0.15
     links
    0.14
     link
    0.14
    /link
    0.13
     linking
    0.12
     href
    0.12
    links
    0.12
    -link
    0.12
     hyperlink
    0.12
    跳转
    0.11
    Activations Density 0.386%

    No Known Activations