© 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. 27-LLAMASCOPE-2-LORSA-16K-K64
    7. 14920
    Prev
    Next
    INDEX
    Explanations

    code

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

    No Comments

    Negative Logits
     Brussels
    -19.13
     creed
    -18.75
    Brad
    -18.75
    bra
    -18.25
     steroids
    -17.88
    翠
    -17.50
    戚
    -17.50
    迳
    -17.50
    ster
    -17.38
     kr
    -17.38
    POSITIVE LOGITS
    Mahon
    18.00
    coh
    17.63
    ej
    17.63
    ATCH
    17.38
    OMP
    17.13
    吐
    16.88
     GHC
    16.13
    vh
    16.13
    eph
    16.00
     Johnson
    15.94
    Activations Density 1.275%

    No Known Activations