© 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. 3288
    Prev
    Next
    INDEX
    Explanations

    energy related terms

    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
    acked
    -0.08
    indsight
    -0.08
    ixel
    -0.08
     Bres
    -0.08
    çµ±ä¸Ģ
    -0.08
    _verbose
    -0.08
    isible
    -0.08
    æIJIJ
    -0.08
    ä¸īçĶŁ
    -0.07
    اضر
    -0.07
    POSITIVE LOGITS
    gett
    0.08
    energy
    0.08
     energy
    0.08
    Energy
    0.08
    lese
    0.07
    _energy
    0.07
    nergy
    0.07
     Energy
    0.07
    ä¼ĺ
    0.07
    èĥ½éĩı
    0.07
    Activations Density 0.007%

    No Known Activations