© 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. 2861
    Prev
    Next
    INDEX
    Explanations

    say "metres"

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

    No Comments

    Negative Logits
     poly
    -22.75
     Poly
    -22.25
    .poly
    -21.75
     Addr
    -21.25
    Poly
    -20.38
    _poly
    -19.13
     Phil
    -18.75
    chap
    -18.75
    (poly
    -18.50
     spec
    -18.38
    POSITIVE LOGITS
     metres
    29.25
     meter
    29.13
     meters
    28.25
     metre
    27.25
    Meter
    27.25
     Meter
    26.88
    计量
    26.13
    -meter
    25.88
    Metrics
    25.63
     metric
    25.25
    Activations Density 0.058%

    No Known Activations