© 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. 14444
    Prev
    Next
    INDEX
    Explanations

    say "ancient Chinese places"

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

    No Comments

    Negative Logits
     Gins
    -19.38
     desn
    -18.13
     Alma
    -18.00
    EMS
    -17.50
     Associates
    -17.50
    mods
    -17.25
    hus
    -16.75
    consin
    -16.63
    单车
    -16.50
    ubs
    -16.38
    POSITIVE LOGITS
    雒
    18.50
     Adri
    18.50
    皇
    18.25
    江东
    18.00
    Cro
    17.88
     Cro
    17.63
     imperial
    17.38
     cro
    16.63
    榆
    16.50
    阆
    16.50
    Activations Density 1.184%

    No Known Activations