© 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. 15772
    Prev
    Next
    INDEX
    Explanations

    say entry

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

    No Comments

    Negative Logits
    orate
    -18.38
     cancelling
    -16.25
    报告
    -15.56
     cancellation
    -15.19
    (report
    -15.06
     reporting
    -15.06
    omit
    -15.00
    -report
    -14.75
    Reporting
    -14.56
     report
    -14.44
    POSITIVE LOGITS
     entry
    56.75
     Entry
    53.25
    entry
    51.00
    <Entry
    50.50
     entrada
    49.50
    	entry
    48.75
    -entry
    48.50
     ENTRY
    48.50
    _Entry
    48.25
    Entry
    47.75
    Activations Density 0.304%

    No Known Activations