© 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. 14975
    Prev
    Next
    INDEX
    Explanations

    newline

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

    No Comments

    Negative Logits
    棋
    -20.38
    HASH
    -18.88
    桂花
    -18.50
    蘧
    -18.50
    漆
    -18.38
    粑
    -18.13
    祺
    -17.88
    润滑
    -17.63
    pix
    -17.38
    pis
    -17.25
    POSITIVE LOGITS
    onda
    20.75
     Sunderland
    19.50
    conc
    19.13
    垄
    19.13
     ANC
    19.13
     Angela
    19.00
    ondo
    18.88
    onde
    18.75
    unge
    18.50
    stant
    18.25
    Activations Density 1.187%

    No Known Activations