© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 10959
    Prev
    Next
    INDEX
    Explanations

    split / splitting / splits

    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
    kad
    -0.09
    IME
    -0.07
    ISTI
    -0.07
    åij¨å²ģ以ä¸Ĭ
    -0.07
    خاÙĦ
    -0.07
    OKIE
    -0.07
    dy
    -0.06
    é¦ģ
    -0.06
     Border
    -0.06
    ecker
    -0.06
    POSITIVE LOGITS
    åĬĪ
    0.09
     splits
    0.09
    -split
    0.09
     splitting
    0.08
    _split
    0.08
    plits
    0.08
     splitted
    0.08
    Split
    0.08
    split
    0.08
     Split
    0.08
    Activations Density 0.002%

    No Known Activations