© 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. 2733
    Prev
    Next
    INDEX
    Explanations

    say "reform"

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

    No Comments

    Negative Logits
     Ser
    -20.25
    Addr
    -20.00
    Ser
    -19.63
    (serial
    -18.63
     ser
    -18.50
    乙方
    -18.38
    (addr
    -18.38
    ser
    -18.00
    -ser
    -18.00
     addr
    -17.88
    POSITIVE LOGITS
    改革
    55.50
     reform
    47.50
     Reform
    39.50
     reforms
    37.50
     rem
    28.88
    深化改革
    28.13
     optimization
    26.88
    制度改革
    26.75
     optimizer
    26.25
    优化
    24.25
    Activations Density 0.206%

    No Known Activations