© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Qwen3-1.7B
    3. 26-LLAMASCOPE-2-LORSA-16K-K64
    4. 1082
    Prev
    Next
    INDEX
    Explanations

    say "Eq"

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

    No Comments

    Negative Logits
     equation
    -49.00
     equations
    -47.25
    Equ
    -45.25
     Equation
    -44.25
     Equ
    -42.25
    方
    -40.75
     equ
    -39.50
    _equ
    -38.00
    equ
    -36.75
    .equ
    -35.25
    POSITIVE LOGITS
     torch
    17.25
    torch
    16.13
    =torch
    16.00
    理发
    15.44
     Mario
    15.25
     fish
    15.13
    药师
    14.56
    บาท
    14.50
    ');");↵
    14.44
    yen
    14.13
    Activations Density 0.129%

    No Known Activations