© 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. 26-LLAMASCOPE-2-LORSA-16K-K64
    7. 1856
    Prev
    Next
    INDEX
    Explanations

    polar => polar bear

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

    No Comments

    Negative Logits
     polar
    -29.50
     Polar
    -26.50
     Arctic
    -25.25
    北极
    -23.63
     polarization
    -23.25
     polarity
    -20.13
     Nordic
    -19.50
     ARP
    -19.25
     arp
    -18.38
     Alaska
    -18.13
    POSITIVE LOGITS
     card
    18.00
     Card
    16.75
    Card
    16.50
    Safe
    16.38
    -ui
    15.94
    unsafe
    15.69
    _ui
    15.31
    JavaScript
    15.31
    _JS
    15.25
    语文
    15.25
    Activations Density 0.119%

    No Known Activations