© 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. 16343
    Prev
    Next
    INDEX
    Explanations

    say home

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

    No Comments

    Negative Logits
    台风
    -16.63
    faces
    -16.50
    风扇
    -16.25
    ApiClient
    -15.81
    Photon
    -15.63
    ImagePath
    -15.44
    电梯
    -15.44
     катал
    -15.31
    蜓
    -15.25
     Channels
    -15.19
    POSITIVE LOGITS
     homeland
    28.38
     home
    27.25
    家园
    26.75
    家乡
    25.00
    (home
    24.00
    土地
    23.50
     Home
    23.50
     homes
    23.38
    土
    22.88
    _home
    22.63
    Activations Density 0.227%

    No Known Activations