© 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. 1141
    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
    鸢
    -18.50
     Erdogan
    -18.38
    眼镜
    -17.63
    芪
    -17.50
     windshield
    -17.50
     Afr
    -17.38
     aba
    -17.38
     quán
    -17.25
    FML
    -17.25
     Abram
    -16.88
    POSITIVE LOGITS
    ্�
    13.94
    ャ
    13.69
    风光
    13.13
    能源
    12.69
    _EV
    12.56
    节能环保
    12.50
    oki
    12.50
    Architecture
    12.44
    itecture
    12.25
    Japan
    12.13
    Activations Density 0.075%

    No Known Activations