© 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. 14679
    Prev
    Next
    INDEX
    Explanations

    measurement units

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

    No Comments

    Negative Logits
    -Con
    -25.00
    -con
    -21.88
     Con
    -21.25
    Con
    -20.13
    _con
    -19.25
     CON
    -18.50
    vince
    -18.13
    jab
    -17.88
    con
    -17.75
     Кон
    -17.50
    POSITIVE LOGITS
    ooter
    18.88
    eus
    15.25
     foot
    14.19
     Braun
    14.00
     Arsenal
    13.94
    光源
    13.94
     Aurora
    13.38
     brun
    13.13
     dark
    12.94
     defaultMessage
    12.88
    Activations Density 0.017%

    No Known Activations