© 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. 27-LLAMASCOPE-2-LORSA-16K-K64
    7. 14919
    Prev
    Next
    INDEX
    Explanations

    say "weakening"

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

    No Comments

    Negative Logits
    GroupId
    -17.63
    愔
    -17.50
     predictions
    -17.38
    LOTS
    -17.25
    predict
    -16.88
     prediction
    -16.75
     UNU
    -16.50
    predictions
    -16.38
    Observers
    -16.38
     predictive
    -16.25
    POSITIVE LOGITS
    进
    16.63
    平衡
    16.00
    单
    15.63
     name
    15.38
    名
    15.25
    纯
    15.19
    单一
    14.88
    结构
    14.81
    名称
    14.50
    支持
    14.13
    Activations Density 0.123%

    No Known Activations