© 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. 27-LLAMASCOPE-2-LORSA-16K-K64
    7. 13968
    Prev
    Next
    INDEX
    Explanations

    say description

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

    No Comments

    Negative Logits
    测量
    -21.25
     measurement
    -20.88
     measurements
    -20.13
    签
    -18.75
     Measurement
    -18.75
    _SIGNAL
    -18.63
     label
    -18.38
    测定
    -18.25
    单位
    -17.88
     Measurements
    -17.88
    POSITIVE LOGITS
    描述
    19.00
    描写
    16.63
     Description
    16.50
    Description
    16.50
    description
    16.38
     description
    16.38
     report
    16.25
    .pack
    16.13
    Desc
    16.00
    "description
    16.00
    Activations Density 0.942%

    No Known Activations