© 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. 2947
    Prev
    Next
    INDEX
    Explanations

    say "preserve"

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

    No Comments

    Negative Logits
    乙方
    -19.38
    =req
    -18.25
    妳
    -16.13
    Vec
    -15.88
    _vec
    -15.75
    叁
    -15.69
     Dem
    -15.38
    贰
    -15.38
    Dem
    -15.25
     Recru
    -15.25
    POSITIVE LOGITS
    Pres
    74.50
     Pres
    70.50
    pres
    68.00
     PRES
    64.50
     pres
    64.50
     preservation
    63.75
    _pres
    61.75
     preserve
    60.75
    .pres
    59.75
     Preservation
    59.25
    Activations Density 0.159%

    No Known Activations