© 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. 15110
    Prev
    Next
    INDEX
    Explanations

    say hex digits

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

    No Comments

    Negative Logits
    RAL
    -23.75
    ALLY
    -23.38
    gow
    -22.88
    ERM
    -22.38
    DMA
    -22.00
    eer
    -21.13
    iture
    -21.00
    ERO
    -20.75
    nym
    -20.75
    ARAM
    -20.50
    POSITIVE LOGITS
    .Hex
    13.25
    โ
    13.25
     transformers
    12.88
     hex
    12.50
    郇
    12.25
     handleChange
    12.00
    遮
    11.38
    .minecraftforge
    11.25
     overhe
    11.13
     Ug
    10.81
    Activations Density 0.011%

    No Known Activations