© 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. 16039
    Prev
    Next
    INDEX
    Explanations

    citation authors

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

    No Comments

    Negative Logits
     Ox
    -48.75
     ox
    -47.25
     AX
    -47.00
    OX
    -46.75
    ox
    -46.75
    XR
    -46.50
     CX
    -46.25
    EX
    -46.00
    xi
    -45.75
    xr
    -45.25
    POSITIVE LOGITS
    山路
    16.25
    몽
    14.63
    篦
    14.56
    ountain
    14.44
    ocha
    14.38
     Tur
    14.38
    芡
    14.19
    埭
    13.81
    甸
    13.75
    眼皮
    13.75
    Activations Density 4.936%

    No Known Activations