© 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. 26504
    Prev
    Next
    INDEX
    Explanations

    global scope or variables

    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
    ä½¼
    -0.08
    -regexp
    -0.07
    ondi
    -0.07
    hofer
    -0.07
    èIJ½äºĨ
    -0.07
    ernas
    -0.07
     defaults
    -0.07
    åĩłç»ı
    -0.06
     근거
    -0.06
    è¶
    -0.06
    POSITIVE LOGITS
    /global
    0.11
     global
    0.11
    -global
    0.10
     Global
    0.10
     globally
    0.10
    åħ¨å±Ģ
    0.10
    Global
    0.09
    GLOBAL
    0.09
    global
    0.09
    .Global
    0.09
    Activations Density 0.113%

    No Known Activations