© 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. 27-LLAMASCOPE-2-LORSA-16K-K64
    7. 15041
    Prev
    Next
    INDEX
    Explanations

    say numbers

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

    No Comments

    Negative Logits
    囊
    -19.88
     bras
    -19.00
    ramid
    -18.63
    lob
    -17.88
     Citizen
    -17.88
     Rath
    -17.38
    .qual
    -17.25
    筒
    -17.25
     submar
    -17.13
    пл
    -17.13
    POSITIVE LOGITS
    ersed
    14.69
    ˌ
    14.00
     Ak
    13.94
    nyder
    13.88
    党政
    13.81
     spoiled
    13.63
    chter
    13.56
     Anders
    13.31
    风光
    13.31
    康熙
    13.19
    Activations Density 1.135%

    No Known Activations