© 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. 1996
    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
     student
    -39.50
     Student
    -37.50
    Student
    -36.50
    学生
    -36.25
    student
    -35.00
    学生的
    -34.75
    学生们
    -32.50
     students
    -32.25
     Students
    -31.50
    _student
    -31.38
    POSITIVE LOGITS
    油
    19.75
     oil
    18.00
     Oil
    17.75
    Oil
    17.63
    矩阵
    17.38
    oracle
    17.13
    -api
    16.50
     Fuk
    15.56
     Oracle
    15.44
    Api
    14.94
    Activations Density 0.195%

    No Known Activations