© 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. 41579
    Prev
    Next
    INDEX
    Explanations

    dye and dyeing

    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
    kort
    -0.07
    rata
    -0.06
     mitig
    -0.06
    å¯ĴåĨ·
    -0.06
    hev
    -0.06
    èĤĺ
    -0.06
     Fabriz
    -0.06
    alian
    -0.06
    åĽłåħ¬
    -0.06
    æīĺ
    -0.06
    POSITIVE LOGITS
     dye
    0.10
    inker
    0.09
     pigment
    0.09
    é¢ľæĸĻ
    0.09
    /color
    0.09
    æ²īçĿĢ
    0.09
    åľ¨æ°´éĩĮ
    0.09
    é«ĺçħ§
    0.09
    iede
    0.08
    é²ľèī³
    0.08
    Activations Density 0.066%

    No Known Activations