© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 15724
    Prev
    Next
    INDEX
    Explanations

    non‑Latin characters

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

    No Comments

    Negative Logits
    -r
    -42.50
    -R
    -40.75
     rs
    -40.25
    RP
    -39.75
     RS
    -39.50
    RS
    -39.25
     rl
    -39.25
     RL
    -38.75
     rf
    -38.75
     RCC
    -38.75
    POSITIVE LOGITS
    epar
    14.69
    apore
    13.63
    骘
    13.06
    ILLS
    12.88
    扫黑
    12.31
    荫
    12.19
    フト
    12.19
    悬浮
    12.19
    毽
    12.13
    潔
    12.06
    Activations Density 4.759%

    No Known Activations