© 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
    2. Qwen3-1.7B
    3. 27-LLAMASCOPE-2-LORSA-16K-K64
    4. 16256
    Prev
    Next
    INDEX
    Explanations

    non‑ASCII characters

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

    No Comments

    Negative Logits
    .Console
    -18.88
    囤
    -17.75
     conservatism
    -17.25
     Prairie
    -17.00
    руд
    -16.50
    monkey
    -16.25
    箬
    -16.25
    龙头企业
    -16.13
     monopol
    -15.56
    工业企业
    -15.56
    POSITIVE LOGITS
    咬
    20.38
    bite
    15.94
    UED
    15.94
    ector
    15.81
    泪
    15.44
     col
    15.31
     UIF
    15.25
    ued
    15.00
    CI
    14.88
    dr
    14.75
    Activations Density 0.769%

    No Known Activations