© 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. 57652
    Prev
    Next
    INDEX
    Explanations

    weighing and balance

    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
     Tanger
    -0.08
    Scoped
    -0.08
    è¯Ńç§į
    -0.07
    交éĽĨ
    -0.07
    ä¹ĭ交
    -0.07
    interfaces
    -0.07
    ä»°
    -0.07
    kki
    -0.07
    ilig
    -0.07
    aspers
    -0.07
    POSITIVE LOGITS
    平衡
    0.14
     balance
    0.13
    ä¸į平衡
    0.12
     Balance
    0.12
    秤
    0.11
    balance
    0.11
    天平
    0.11
     imbalance
    0.11
     balanced
    0.11
    Balance
    0.11
    Activations Density 0.004%

    No Known Activations