© 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. 20777
    Prev
    Next
    INDEX
    Explanations

    differential cross sections

    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
    åµĮ
    -0.09
    åįĹåĽ½
    -0.07
    çºł
    -0.07
    obil
    -0.07
    åµĮåħ¥
    -0.07
    PageIndex
    -0.07
    åı°ä¸ĭ
    -0.06
    ĥĿ
    -0.06
    å¤ļ说
    -0.06
    ä¸įè°Ī
    -0.06
    POSITIVE LOGITS
    ":[{"
    0.08
    天å®Ŀ
    0.08
    nyi
    0.07
    outers
    0.07
     raci
    0.07
    į°
    0.07
    åĵĹ
    0.07
    lici
    0.07
    ennie
    0.07
    åĸ½
    0.07
    Activations Density 0.002%

    No Known Activations