© 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. 14636
    Prev
    Next
    INDEX
    Explanations

    say communication

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

    No Comments

    Negative Logits
    itur
    -18.75
    ExecutionContext
    -17.63
    조사
    -16.25
    調查
    -16.25
     перев
    -16.13
    executable
    -16.00
    domains
    -15.94
     Susp
    -15.88
    Domains
    -15.50
     dominates
    -15.44
    POSITIVE LOGITS
    周三
    14.69
    接触
    14.13
     communication
    13.88
    联系
    13.81
    沟通
    13.69
     generated
    13.63
    浅
    13.63
    _PROTOCOL
    13.44
     Communication
    13.31
    元素
    13.19
    Activations Density 0.111%

    No Known Activations