© 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
    2. Qwen3-1.7B
    3. 26-LLAMASCOPE-2-LORSA-16K-K64
    4. 1851
    Prev
    Next
    INDEX
    Explanations

    cash

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

    No Comments

    Negative Logits
     cash
    -39.25
    现金
    -36.75
     Cash
    -35.75
    cash
    -35.25
    Cash
    -35.00
    _cash
    -30.75
    现金流
    -30.63
     csv
    -24.50
    csv
    -24.00
     CSV
    -23.50
    POSITIVE LOGITS
     Di
    17.00
    Di
    16.63
     Ball
    15.38
     di
    15.00
    fc
    14.81
    edic
    14.50
     Martial
    14.44
    read
    14.38
    钢铁
    14.19
    (arc
    14.06
    Activations Density 0.048%

    No Known Activations