© 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. 2161
    Prev
    Next
    INDEX
    Explanations

    say double t

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

    No Comments

    Negative Logits
    乙
    -24.25
    乙方
    -21.50
    甲
    -21.38
     Meth
    -20.88
     Mer
    -20.63
    策略
    -19.25
    mer
    -19.00
     strategy
    -19.00
     Strategy
    -18.88
    Mer
    -18.75
    POSITIVE LOGITS
     Terr
    22.00
    comm
    21.00
     Comm
    20.88
    	curr
    20.63
    Terr
    20.25
    (comm
    18.75
     att
    18.63
     comm
    18.63
     curr
    18.50
    Comm
    18.50
    Activations Density 0.255%

    No Known Activations