© 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. 15472
    Prev
    Next
    INDEX
    Explanations

    say flow

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

    No Comments

    Negative Logits
    olk
    -16.88
    ogne
    -16.50
     śl
    -15.69
    щин
    -15.63
    Support
    -15.44
    配置
    -15.38
    慰
    -15.25
    护肤
    -15.19
    unter
    -15.13
    onder
    -15.00
    POSITIVE LOGITS
    flow
    22.75
    -flow
    20.50
     Flow
    20.38
     flow
    20.00
    .Flow
    19.50
    Flow
    19.00
    流向
    18.63
    vert
    18.25
    _flow
    18.25
     flows
    17.38
    Activations Density 0.156%

    No Known Activations