© 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. 27-LLAMASCOPE-2-LORSA-16K-K64
    7. 14485
    Prev
    Next
    INDEX
    Explanations

    Chinese nouns

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

    No Comments

    Negative Logits
    (gs
    -14.31
     realise
    -13.63
    EObject
    -13.50
     recognise
    -13.44
    .Dictionary
    -13.25
    .spinner
    -12.94
     Georgian
    -12.94
    inus
    -12.88
    _GF
    -12.75
    ёр
    -12.75
    POSITIVE LOGITS
    城市
    19.00
    TH
    18.00
    ancial
    16.88
    Cl
    16.75
    Cold
    16.63
    女孩
    16.50
    女性
    15.94
    城市发展
    15.56
    水
    15.44
     Wenger
    15.44
    Activations Density 0.355%

    No Known Activations