© 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
    2. Qwen3-1.7B
    3. 27-LLAMASCOPE-2-LORSA-16K-K64
    4. 15719
    Prev
    Next
    INDEX
    Explanations

    say "percent"

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

    No Comments

    Negative Logits
    ldb
    -18.38
    籽
    -17.88
    addField
    -17.00
     hookup
    -16.75
    Knife
    -16.50
     stepper
    -16.50
     Gibson
    -16.00
    督导
    -15.88
    導
    -15.81
    (gr
    -15.69
    POSITIVE LOGITS
     percent
    29.63
    _percent
    27.38
    percent
    26.50
    Percent
    26.00
     Percent
    25.75
    百分
    25.75
     perc
    25.00
     percentage
    25.00
     percentages
    25.00
    .percent
    24.50
    Activations Density 0.163%

    No Known Activations