© 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. 47152
    Prev
    Next
    INDEX
    Explanations

    mathematical and computational concepts

    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
    icha
    -0.08
    herits
    -0.07
    ramework
    -0.07
    [](
    -0.07
    angi
    -0.07
    é¦ĸåľº
    -0.07
     papar
    -0.07
    ongen
    -0.07
    luss
    -0.06
    andler
    -0.06
    POSITIVE LOGITS
     auxiliary
    0.08
     calculations
    0.08
     relationships
    0.08
    implicit
    0.08
     computations
    0.07
     notation
    0.07
     counter
    0.07
     mathematical
    0.07
     ratios
    0.07
     coordinate
    0.07
    Activations Density 0.187%

    No Known Activations