© 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. 24849
    Prev
    Next
    INDEX
    Explanations

    names and game events

    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
     Pett
    -0.08
    麦
    -0.07
    umed
    -0.07
    isit
    -0.07
    -placement
    -0.07
    Dirs
    -0.06
    imt
    -0.06
    /name
    -0.06
     manifest
    -0.06
    obat
    -0.06
    POSITIVE LOGITS
    asca
    0.08
    رتÙĪÙĨ
    0.07
    纲è¦ģ
    0.07
    ater
    0.07
    erture
    0.07
    çĤ¹åĩ»ä¸Ĭæĸ¹
    0.07
    голо
    0.07
    oland
    0.06
    aters
    0.06
     Sullivan
    0.06
    Activations Density 0.755%

    No Known Activations