© 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. 15646
    Prev
    Next
    INDEX
    Explanations

    say morning

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

    No Comments

    Negative Logits
    威胁
    -18.00
    xFD
    -16.75
     Threat
    -16.50
     defender
    -16.13
    threat
    -16.00
    PCI
    -16.00
     Rhodes
    -15.94
    保利
    -15.81
     PCI
    -15.75
    security
    -15.63
    POSITIVE LOGITS
    晨
    20.75
     Morning
    20.38
     morning
    19.63
    上午
    18.75
     breakfast
    18.63
    醒
    18.63
     sunrise
    18.00
     Dawn
    17.38
    _sun
    17.13
     Wake
    16.50
    Activations Density 0.255%

    No Known Activations