© 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. 15459
    Prev
    Next
    INDEX
    Explanations

    indicator _MARKER

    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
    æĪĸ缴æİ¥
    -0.07
    egu
    -0.06
     seemingly
    -0.06
     DÃŃ
    -0.06
    ouser
    -0.06
    -0.06
    çļĨ为
    -0.06
    ippy
    -0.06
    ä¸ĸçķĮ级
    -0.06
     e
    -0.06
    POSITIVE LOGITS
    represented
    0.12
     ditandai
    0.12
     represented
    0.12
     indicated
    0.11
    çĶ¨ä¸Ģ个
    0.10
    åĨĻåľ¨
    0.10
    ãĤĴ表
    0.10
    _indicator
    0.10
    _MARKER
    0.10
    ãĤĴ示
    0.10
    Activations Density 0.320%

    No Known Activations