© 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. 15617
    Prev
    Next
    INDEX
    Explanations

    say "resource" words

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

    No Comments

    Negative Logits
     enqu
    -16.25
     SqlCommand
    -16.00
    iegel
    -15.75
     hooks
    -15.50
    êm
    -15.19
    .Debugger
    -14.94
    vro
    -14.81
    icers
    -14.75
    的妻子
    -14.69
    _sold
    -14.63
    POSITIVE LOGITS
    资源
    74.50
     resource
    68.50
     resources
    67.50
     Resource
    62.25
    resource
    62.25
    資源
    61.25
     Resources
    59.75
    Resource
    59.75
    resources
    58.75
    _resource
    57.00
    Activations Density 0.498%

    No Known Activations