© 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. 26-LLAMASCOPE-2-LORSA-16K-K64
    7. 580
    Prev
    Next
    INDEX
    Explanations

    say facilities

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

    No Comments

    Negative Logits
    ORB
    -16.63
     LIC
    -16.13
    IVA
    -16.00
    代言
    -16.00
    DSL
    -15.94
    ollision
    -15.94
    (GUI
    -15.63
    碰撞
    -15.50
    collision
    -15.50
     comercial
    -15.44
    POSITIVE LOGITS
     toilets
    22.00
    床
    20.63
    厕所
    19.88
    厨房
    18.75
     rooms
    18.50
    锅炉
    18.25
    帐篷
    18.13
     py
    17.88
    食堂
    17.88
     Laundry
    17.63
    Activations Density 0.156%

    No Known Activations