© 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. 27-LLAMASCOPE-2-LORSA-16K-K64
    7. 14448
    Prev
    Next
    INDEX
    Explanations

    code snippets

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

    No Comments

    Negative Logits
    alsa
    -27.13
    黑龙
    -24.63
    fce
    -20.38
    pls
    -19.88
    cycl
    -19.75
    捕捉
    -19.75
    梅西
    -19.63
     AHL
    -19.50
     Johnson
    -19.50
     MLS
    -19.38
    POSITIVE LOGITS
    aret
    20.50
    bare
    20.13
     Kirk
    17.88
    炜
    17.88
     arb
    17.63
     Pare
    17.63
    arem
    17.50
     Lam
    17.25
    (AdapterView
    17.25
     Lar
    17.13
    Activations Density 1.238%

    No Known Activations