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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-1.7B
    5. 27-LLAMASCOPE-2-LORSA-16K-K64
    7. 13988
    Prev
    Next
    INDEX
    Explanations

    say suffixes

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

    No Comments

    Negative Logits
    发表
    -22.38
    報導
    -21.25
    报道
    -20.75
     publication
    -20.38
    刊登
    -19.00
    representation
    -19.00
    REPORT
    -18.75
     representations
    -18.38
     representation
    -18.38
    reports
    -18.25
    POSITIVE LOGITS
    -road
    14.50
    伙伴关系
    14.44
    _Profile
    14.13
    ixe
    14.00
    iev
    13.94
    彈
    13.88
    Session
    13.88
    -proof
    13.75
    修正
    13.63
    _session
    13.50
    Activations Density 1.112%

    No Known Activations