© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-1.7B
    5. 26-LLAMASCOPE-2-LORSA-16K-K64
    7. 1248
    Prev
    Next
    INDEX
    Explanations

    Chinese provinces

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

    No Comments

    Negative Logits
    云
    -17.25
    云计算
    -16.75
     Cloud
    -16.63
    cloud
    -16.38
     Church
    -16.25
     cloud
    -16.13
    Python
    -15.44
    /cloud
    -15.31
    python
    -15.06
    软件
    -14.94
    POSITIVE LOGITS
    木质
    16.75
     MATERIAL
    16.63
    .ham
    16.38
     Amar
    16.38
     Materials
    16.25
    spiel
    15.56
    quirer
    15.56
    cdc
    15.38
    ahir
    15.19
    �
    15.06
    Activations Density 0.090%

    No Known Activations