© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-1.7B
    5. 26-LLAMASCOPE-2-LORSA-16K-K64
    7. 3025
    Prev
    Next
    INDEX
    Explanations

    say "nav" tokens

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

    No Comments

    Negative Logits
    许
    -21.00
     Emerson
    -20.88
    (em
    -20.50
     Gilbert
    -18.75
    苔
    -18.38
     berg
    -17.50
     emitter
    -17.25
    顺德
    -17.13
     Melissa
    -17.00
    PTY
    -16.88
    POSITIVE LOGITS
     nav
    34.00
    (nav
    29.50
     Nav
    29.50
    Nav
    28.13
    _nav
    26.13
    nav
    25.88
    /nav
    24.00
    .nav
    23.50
    .Nav
    22.38
     NAV
    19.50
    Activations Density 0.022%

    No Known Activations