© 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. 14276
    Prev
    Next
    INDEX
    Explanations

    say procession

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

    No Comments

    Negative Logits
    文档
    -17.75
    瓠
    -16.63
    PING
    -16.50
    教育资源
    -16.25
    窒
    -16.25
    internet
    -16.00
    /rfc
    -15.31
    投资项目
    -15.31
     terminology
    -15.25
     McM
    -15.25
    POSITIVE LOGITS
     procession
    26.38
    process
    21.75
     process
    21.63
     parade
    21.50
     Parade
    21.38
     Process
    20.63
     march
    20.50
     proces
    20.38
    Process
    19.63
    过程
    19.50
    Activations Density 0.651%

    No Known Activations