© 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. 15610
    Prev
    Next
    INDEX
    Explanations

    say oath

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

    No Comments

    Negative Logits
     Harper
    -19.63
    香菇
    -19.25
    _skin
    -18.75
    不平衡
    -16.75
    antz
    -16.38
    _processors
    -16.25
    皮肤
    -16.25
    craper
    -16.13
    processors
    -16.13
    qc
    -16.13
    POSITIVE LOGITS
    承诺
    33.00
    誓
    31.63
     pledge
    31.00
     vows
    30.38
    誓言
    29.00
     oath
    28.88
     vow
    28.88
     pledges
    28.63
     promise
    27.63
     promises
    26.75
    Activations Density 0.265%

    No Known Activations