© 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. 7739
    Prev
    Next
    INDEX
    Explanations

    programming constructs (e.g., objects, functions, modules)

    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
    olson
    -0.08
    cpy
    -0.08
    bli
    -0.08
    ä¾ĽåºĶ产åĵģ
    -0.08
    ắng
    -0.08
    å±ħ
    -0.08
    kbd
    -0.08
    رÙĬÙĨ
    -0.08
    å¾Īå¤ļæľĭåıĭ
    -0.07
    ksz
    -0.07
    POSITIVE LOGITS
    æĪĸåĽł
    0.06
    okie
    0.06
     Indo
    0.06
    ster
    0.06
    ↵
    0.06
     رÙĥ
    0.05
     tune
    0.05
     surve
    0.05
    VENT
    0.05
    åĽłäºº
    0.05
    Activations Density 0.258%

    No Known Activations