© 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. 34206
    Prev
    Next
    INDEX
    Explanations

    which introduces a definition or clause

    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
    ses
    -0.08
     λοι
    -0.07
     vs
    -0.07
    عÙĬ
    -0.07
    stitutions
    -0.07
     donc
    -0.07
    olds
    -0.07
    ä¸įäºĨ
    -0.06
    orna
    -0.06
    USED
    -0.06
    POSITIVE LOGITS
     which
    0.11
    which
    0.09
    ÏĢοÏħ
    0.09
     wherein
    0.09
     коÑĤоÑĢаÑı
    0.08
     consisting
    0.08
     specifically
    0.08
     коÑĤоÑĢое
    0.08
     particularly
    0.08
     wich
    0.08
    Activations Density 0.156%

    No Known Activations