© 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. 14263
    Prev
    Next
    INDEX
    Explanations

    say plan

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

    No Comments

    Negative Logits
     transfer
    -26.00
     transfers
    -24.50
     Transfer
    -24.50
    Transfer
    -24.00
    transfer
    -23.88
    -transfer
    -23.00
     transferring
    -22.13
    .Transfer
    -22.00
    .transfer
    -21.75
    _transfer
    -21.50
    POSITIVE LOGITS
     plans
    18.38
    计划
    17.88
     Plan
    17.00
    計劃
    16.75
     plan
    16.50
     Plans
    16.38
    創
    15.56
     CreateMap
    15.50
     Creator
    15.44
    plans
    15.44
    Activations Density 2.391%

    No Known Activations