© 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. 45718
    Prev
    Next
    INDEX
    Explanations

    universal followed by noun

    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
    eworthy
    -0.09
    eger
    -0.09
    estu
    -0.09
    manship
    -0.08
    åľĨ梦
    -0.08
    ew
    -0.08
    Ø©
    -0.08
    GLOBALS
    -0.08
    åĽŀäºĭ
    -0.08
    åħ·åIJĪ
    -0.08
    POSITIVE LOGITS
    izing
    0.13
    ized
    0.11
    izable
    0.10
     تÙĤرÙĬب
    0.10
    ization
    0.09
    ocity
    0.09
    ible
    0.09
    ity
    0.09
    idade
    0.09
    iversal
    0.09
    Activations Density 0.013%

    No Known Activations