© 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. 968
    Prev
    Next
    INDEX
    Explanations

    archaic language

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

    No Comments

    Negative Logits
     Hayden
    -19.25
    …)↵↵
    -18.88
     Zimmer
    -18.75
     Lawson
    -18.75
     Gallagher
    -18.50
    Howard
    -18.50
     Lowell
    -18.38
     Hoover
    -18.25
     Marriott
    -18.25
    lü
    -18.13
    POSITIVE LOGITS
     �
    15.00
    颛
    14.44
    uc
    14.00
     Romans
    13.94
     sal
    13.69
     gods
    13.63
    虔
    13.31
     orb
    13.31
    旨
    13.31
    cer
    13.13
    Activations Density 0.212%

    No Known Activations