© 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. 14016
    Prev
    Next
    INDEX
    Explanations

    say oil

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

    No Comments

    Negative Logits
    amac
    -17.13
    Wnd
    -16.75
    _FRIEND
    -16.50
    听课
    -16.00
    CW
    -15.38
    细胞
    -15.19
    .Slice
    -15.13
    Friend
    -15.13
    寝室
    -15.13
    AW
    -15.00
    POSITIVE LOGITS
    油
    38.25
     oil
    37.75
     Oil
    35.50
    石油
    34.75
    Oil
    33.75
     dầu
    32.25
    油价
    32.00
    油田
    31.75
    油气
    31.38
    oil
    30.50
    Activations Density 0.475%

    No Known Activations