© 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. 11650
    Prev
    Next
    INDEX
    Explanations

    energy and its related concepts

    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
    ovid
    -0.08
    è¿Ļæł¹
    -0.07
    ловиÑĩ
    -0.07
    lear
    -0.07
    кÑĥÑĢÑģ
    -0.07
    ÙĥÙĪر
    -0.07
    ynek
    -0.07
    Ñĥз
    -0.07
    åĭĥ
    -0.07
    OLON
    -0.07
    POSITIVE LOGITS
    èĥ½éĩı
    0.10
     energy
    0.09
    _energy
    0.09
    energy
    0.09
     ÑįнеÑĢгиÑİ
    0.08
    èĥ½éĩıçļĦ
    0.08
    大åĬŁ
    0.08
     ÑįнеÑĢгии
    0.08
     ενÎŃÏģγ
    0.08
     Energy
    0.08
    Activations Density 0.013%

    No Known Activations