© 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. 2926
    Prev
    Next
    INDEX
    Explanations

    color and coloring

    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
    åĩ«
    -0.08
    æ²īæµ®
    -0.07
     contracts
    -0.07
    ekut
    -0.07
     morphology
    -0.06
    裹
    -0.06
    caled
    -0.06
    æıIJæIJº
    -0.06
    iled
    -0.06
    åħĪè¾Ī
    -0.06
    POSITIVE LOGITS
     Coloring
    0.09
     coloring
    0.09
    æŁĵ
    0.09
     colors
    0.09
    çĿĢèī²
    0.09
    .getColor
    0.09
    /color
    0.09
    Colors
    0.09
    olor
    0.08
    colors
    0.08
    Activations Density 0.007%

    No Known Activations