© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-1.7B
    5. 27-LLAMASCOPE-2-LORSA-16K-K64
    7. 15672
    Prev
    Next
    INDEX
    Explanations

    upward mobility

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

    No Comments

    Negative Logits
    dek
    -16.63
    .instructions
    -16.38
    dde
    -16.13
    Instruction
    -15.69
    /fw
    -15.44
    coil
    -15.38
    YNC
    -15.25
    edReader
    -15.00
     instructions
    -14.81
    instruction
    -14.75
    POSITIVE LOGITS
    晋升
    26.38
    晋级
    20.13
    机会
    19.88
    privileged
    19.75
     Priv
    19.50
     mobility
    19.50
    通行证
    19.50
     Elev
    19.13
     privilege
    19.00
    阶
    18.25
    Activations Density 0.379%

    No Known Activations