© 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
    3. Qwen3-1.7B
    5. 27-LLAMASCOPE-2-LORSA-16K-K64
    7. 15662
    Prev
    Next
    INDEX
    Explanations

    say Chinese characters

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

    No Comments

    Negative Logits
    TER
    -37.50
    erer
    -37.50
    BER
    -37.50
    jer
    -37.25
    erner
    -36.50
    ER
    -35.75
    cer
    -35.75
     BER
    -35.00
     ER
    -34.50
     Ner
    -34.50
    POSITIVE LOGITS
    瘸
    20.88
    郗
    20.00
    镖
    19.00
    溆
    18.88
    苋
    18.13
    淀
    17.38
    邾
    17.13
    缅甸
    17.00
    郏
    17.00
    淇
    16.88
    Activations Density 5.318%

    No Known Activations