© 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. 15502
    Prev
    Next
    INDEX
    Explanations

    code formatting or structure

    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
    <html
    -0.06
    fare
    -0.06
    ovsky
    -0.06
     اÙĦÙİÙijØ°ÙIJÙĬÙĨÙİ
    -0.06
    illing
    -0.06
    adge
    -0.06
    é¡Į
    -0.06
    mods
    -0.06
    禹
    -0.06
    äºĭ件çļĦ
    -0.06
    POSITIVE LOGITS
    缸è¾ħ缸æĪIJ
    0.08
    ró
    0.07
    onga
    0.07
    sche
    0.07
    ãĢģãĢİ
    0.07
    ppe
    0.07
    arro
    0.07
     aray
    0.07
    -toolbar
    0.07
    erci
    0.07
    Activations Density 0.113%

    No Known Activations