© 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. 2257
    Prev
    Next
    INDEX
    Explanations

    say "sim"

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

    No Comments

    Negative Logits
    注册
    -19.13
    	register
    -18.63
     Registered
    -17.50
    结算
    -17.50
     Segment
    -17.38
    註冊
    -17.38
     registered
    -17.00
     segment
    -16.25
     register
    -16.00
    .register
    -16.00
    POSITIVE LOGITS
    模拟
    51.50
     sim
    49.00
     mim
    47.75
     Mim
    46.00
    (sim
    45.75
    Sim
    44.25
    sim
    43.50
     mimic
    42.25
     Sim
    40.50
     sims
    39.25
    Activations Density 0.154%

    No Known Activations