© 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. 48362
    Prev
    Next
    INDEX
    Explanations

    competitions and classifications

    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
    ilter
    -0.07
    ibat
    -0.06
    áng
    -0.06
    被æīĵ
    -0.06
    大èĢĮ
    -0.06
     запи
    -0.06
    HasKey
    -0.06
    othing
    -0.06
    ensis
    -0.06
    彩çĶµ
    -0.06
    POSITIVE LOGITS
    AtA
    0.08
    arik
    0.08
    á»ıng
    0.08
    è¯Ħä»·ä½ĵç³»
    0.08
    idan
    0.08
    isht
    0.07
    ÏģÏĮÏĤ
    0.07
    cott
    0.07
    ls
    0.07
     GLsizei
    0.07
    Activations Density 0.001%

    No Known Activations