© 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. 2691
    Prev
    Next
    INDEX
    Explanations

    方

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

    No Comments

    Negative Logits
    (ep
    -18.38
     ép
    -17.50
    ep
    -16.75
    lando
    -16.50
     ep
    -16.13
    	ep
    -15.81
    Resume
    -15.75
     reserv
    -15.69
     reserve
    -15.31
     Curriculum
    -15.25
    POSITIVE LOGITS
    方
    70.50
    对方
    52.00
     方
    51.75
     eq
    50.00
    Equ
    45.75
    eq
    45.75
    双方
    45.50
    ⽅
    44.75
     Equ
    44.25
     Eq
    44.25
    Activations Density 0.160%

    No Known Activations