© 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. 28493
    Prev
    Next
    INDEX
    Explanations

    conversations using "I"

    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
    èIJ
    -0.07
    漪
    -0.07
    翱
    -0.06
    ↵
    -0.06
    ask
    -0.06
    å´©
    -0.06
    ä¸Ģå¼ł
    -0.06
    context
    -0.06
     Ùħرک
    -0.06
    ondo
    -0.06
    POSITIVE LOGITS
    ERN
    0.08
    erable
    0.08
     pétr
    0.08
     عاج
    0.08
    大ä¸Ń
    0.08
    ä»·çļĦ
    0.08
    üren
    0.08
    anke
    0.08
    为äºĨå®ŀçİ°
    0.08
    ãģĹãĤĩ
    0.08
    Activations Density 0.006%

    No Known Activations