© 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. 14467
    Prev
    Next
    INDEX
    Explanations

    say "1"

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

    No Comments

    Negative Logits
    xia
    -20.25
    eries
    -19.50
    uers
    -18.75
    urger
    -18.38
    eria
    -18.25
    uten
    -17.63
    cken
    -17.00
    围棋
    -17.00
    uer
    -16.63
    есс
    -16.63
    POSITIVE LOGITS
    �
    17.50
     DeV
    16.88
    �
    16.38
    imb
    15.31
     Alv
    14.69
     Sawyer
    14.56
    邰
    14.56
     Maj
    14.31
     Silva
    14.00
    鄞
    14.00
    Activations Density 0.042%

    No Known Activations