© 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. 16456
    Prev
    Next
    INDEX
    Explanations

    energy and power 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
    siz
    -0.08
    éłĨ
    -0.08
    èį¼
    -0.08
    althy
    -0.08
    aix
    -0.07
    ocht
    -0.07
    FML
    -0.07
    æļ´åĪ©
    -0.07
    _rest
    -0.07
     COMER
    -0.07
    POSITIVE LOGITS
     input
    0.07
     impro
    0.07
     gross
    0.07
     Net
    0.07
    /input
    0.07
    çļĦåħ¨éĥ¨
    0.07
    åĩĢ
    0.07
    umen
    0.07
     Gross
    0.07
     upstream
    0.07
    Activations Density 0.009%

    No Known Activations