© 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. 26-LLAMASCOPE-2-LORSA-16K-K64
    7. 2402
    Prev
    Next
    INDEX
    Explanations

    say "equ"

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

    No Comments

    Negative Logits
    ‖
    -15.56
     capped
    -14.50
    (Pos
    -14.44
    perms
    -14.38
     Pen
    -14.38
    .ctx
    -14.13
    -rad
    -13.94
    Ctx
    -13.81
    še
    -13.75
    SEN
    -13.63
    POSITIVE LOGITS
     equ
    72.50
    方
    68.00
    Equ
    68.00
     Equ
    66.00
     eq
    62.25
    equ
    59.75
    eq
    58.50
    (eq
    55.75
    .eq
    55.50
    _equ
    54.75
    Activations Density 0.162%

    No Known Activations