© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Qwen3-1.7B
    3. 27-LLAMASCOPE-2-LORSA-16K-K64
    4. 15484
    Prev
    Next
    INDEX
    Explanations

    say "levels"

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

    No Comments

    Negative Logits
    温度
    -19.88
     temperature
    -19.63
    溫
    -19.25
     thermal
    -18.38
    发热
    -18.25
     Temperature
    -18.00
    thermal
    -17.75
     temperatures
    -17.50
    emperature
    -16.88
    temperature
    -16.75
    POSITIVE LOGITS
    层面
    19.38
    四级
    18.88
    amax
    18.50
    (strategy
    18.13
     levels
    18.00
     layers
    17.38
    层
    17.13
    宝藏
    17.13
    战略
    16.75
    Levels
    16.50
    Activations Density 0.125%

    No Known Activations