© 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. 27-LLAMASCOPE-2-LORSA-16K-K64
    7. 14021
    Prev
    Next
    INDEX
    Explanations

    say background

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

    No Comments

    Negative Logits
    /rfc
    -16.50
    看病
    -16.25
    病理
    -14.94
     diagn
    -14.81
     lookout
    -14.63
    治疗方法
    -14.44
     Klo
    -14.25
     discriminate
    -14.19
    opathic
    -14.06
    袢
    -14.00
    POSITIVE LOGITS
    背景
    23.75
     background
    21.13
    background
    19.88
     Background
    19.38
    BACKGROUND
    18.00
    uien
    17.88
     backgrounds
    17.00
    Background
    17.00
    	background
    16.88
    (background
    16.25
    Activations Density 0.491%

    No Known Activations