© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-1.7B
    5. 26-LLAMASCOPE-2-LORSA-16K-K64
    7. 1467
    Prev
    Next
    INDEX
    Explanations

    say construction terms

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

    No Comments

    Negative Logits
     building
    -55.50
     build
    -55.00
     Build
    -54.50
    Build
    -54.00
    build
    -53.00
     BUILD
    -52.25
     Building
    -52.25
     builds
    -51.75
    Building
    -50.75
     Builds
    -50.75
    POSITIVE LOGITS
    豨
    13.88
    豹
    13.69
    CD
    13.56
     European
    13.44
     Kra
    12.94
     CD
    12.94
     Europe
    12.88
    瞋
    12.38
     polynomial
    12.25
     Signal
    12.19
    Activations Density 0.345%

    No Known Activations