© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-1.7B
    5. 26-LLAMASCOPE-2-LORSA-16K-K64
    7. 2836
    Prev
    Next
    INDEX
    Explanations

    围

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

    No Comments

    Negative Logits
    riz
    -17.88
    oui
    -17.00
    cia
    -16.50
    焱
    -16.50
    app
    -16.50
     Emm
    -16.50
    湯
    -16.38
     Kant
    -16.38
    URY
    -16.25
     des
    -16.13
    POSITIVE LOGITS
    围
    59.25
    圍
    42.75
    Per
    27.00
     Per
    26.75
    /per
    24.38
    rep
    24.25
    _per
    23.50
    (per
    23.38
     tet
    23.25
    per
    22.75
    Activations Density 0.038%

    No Known Activations