© 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. 1923
    Prev
    Next
    INDEX
    Explanations

    personality

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

    No Comments

    Negative Logits
     headers
    -18.50
    Css
    -17.88
    security
    -17.38
    /Header
    -17.25
     proteins
    -17.13
     jerseys
    -16.75
    <header
    -16.63
    iov
    -16.63
     Header
    -16.50
     playing
    -16.38
    POSITIVE LOGITS
    =torch
    20.75
     Oracle
    19.38
    oracle
    17.38
    .oracle
    17.13
     torch
    17.00
    acd
    16.50
    torch
    16.38
    Doctor
    16.38
     photograph
    16.00
    doctor
    16.00
    Activations Density 0.198%

    No Known Activations