© 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. 2237
    Prev
    Next
    INDEX
    Explanations

    resume

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

    No Comments

    Negative Logits
    SWG
    -19.25
    万辆
    -18.38
     airplanes
    -17.25
    马力
    -17.25
    elib
    -17.25
     Beds
    -17.25
     beds
    -17.00
    bed
    -16.75
    教室
    -16.75
    soles
    -16.63
    POSITIVE LOGITS
    招聘
    36.25
     recruiter
    33.75
     recruiters
    32.75
    求职
    32.50
    简历
    32.50
     hiring
    31.75
     job
    30.50
     Recru
    29.88
    Job
    29.38
     Hiring
    29.13
    Activations Density 0.124%

    No Known Activations