© 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. 26-LLAMASCOPE-2-LORSA-16K-K64
    4. 583
    Prev
    Next
    INDEX
    Explanations

    say equations

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

    No Comments

    Negative Logits
    #\
    -17.75
    \xe
    -17.75
    \xf
    -17.63
    瑟
    -17.63
    \">\
    -17.63
    \xc
    -17.50
    \application
    -17.13
    找工作
    -17.13
    就业岗位
    -16.75
    >\
    -16.50
    POSITIVE LOGITS
     �
    20.50
     equation
    18.63
    ψ
    18.38
    式
    17.13
    ω
    16.88
    Ω
    16.13
     equations
    16.00
    Ui
    16.00
    园
    16.00
     Equation
    15.75
    Activations Density 0.184%

    No Known Activations