© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-1.7B
    5. 26-LLAMASCOPE-2-LORSA-16K-K64
    7. 936
    Prev
    Next
    INDEX
    Explanations

    say "energy"

    unknown · unknown
    New Auto-Interp
    Top Features by Cosine Similarity
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    _TAC
    -18.63
    EIF
    -17.38
    롤
    -16.63
    AdminController
    -16.50
    烟
    -15.69
    檩
    -15.56
    wg
    -15.44
    税
    -15.25
    Mvc
    -15.19
     Kinder
    -15.19
    POSITIVE LOGITS
     energies
    23.38
    能量
    22.25
     energy
    21.88
     energetic
    20.63
     ener
    20.50
    -energy
    19.88
    的能量
    19.75
    エネルギー
    19.50
     Energy
    19.38
     Kund
    19.38
    Activations Density 0.526%

    No Known Activations