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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-1.7B
    5. 26-LLAMASCOPE-2-LORSA-16K-K64
    7. 123
    Prev
    Next
    INDEX
    Explanations

    language learning

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

    No Comments

    Negative Logits
     MSS
    -20.50
     cavalry
    -17.75
    (ms
    -16.13
    MMC
    -15.63
     clothes
    -15.56
    ounty
    -15.50
    车队
    -15.50
     CCT
    -15.38
     textile
    -15.13
     Carpenter
    -15.13
    POSITIVE LOGITS
    语法
    26.75
     learners
    25.25
    汉语
    24.63
     gramm
    23.50
    语言
    23.50
     learner
    23.38
    的语言
    23.00
     grammar
    22.75
     Languages
    22.38
    Languages
    21.50
    Activations Density 0.146%

    No Known Activations