© 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. 46451
    Prev
    Next
    INDEX
    Explanations

    verb endings: -ize, -ization, -ified

    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
    losure
    -0.07
    ters
    -0.07
    ÙĨدگاÙĨ
    -0.07
    алÑĮнаÑı
    -0.07
    éĢļ
    -0.07
    алÑĮнÑĭй
    -0.06
    ajÄħca
    -0.06
    äºij天
    -0.06
    ajÄħcy
    -0.06
    _HAND
    -0.06
    POSITIVE LOGITS
    izes
    0.12
    ized
    0.12
    ize
    0.12
    izing
    0.11
    istically
    0.11
    åĮĸçļĦ
    0.11
    ifies
    0.11
    åĮĸåĴĮ
    0.11
    åĮĸäºĨ
    0.10
    ization
    0.10
    Activations Density 0.126%

    No Known Activations