© 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. 14022
    Prev
    Next
    INDEX
    Explanations

    say source

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

    No Comments

    Negative Logits
    协会
    -15.63
    面条
    -14.94
    乘坐
    -14.81
    協會
    -14.31
    写道
    -14.31
    kest
    -14.00
    守护
    -13.75
    utomation
    -13.75
    掌门
    -13.75
     computations
    -13.63
    POSITIVE LOGITS
    源
    79.00
     source
    77.00
     sources
    76.50
    source
    69.50
    sources
    69.00
     Source
    68.00
    Source
    66.50
     Sources
    66.50
     SOURCE
    65.50
    	source
    64.50
    Activations Density 1.211%

    No Known Activations