© 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. 2109
    Prev
    Next
    INDEX
    Explanations

    say polar

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

    No Comments

    Negative Logits
    =req
    -21.25
    :req
    -21.13
    =msg
    -19.63
    .req
    -18.38
    乙方
    -18.13
     req
    -17.63
     resp
    -17.38
    [msg
    -17.00
     btn
    -16.88
    (msg
    -16.88
    POSITIVE LOGITS
     polar
    68.50
     Polar
    62.75
    极
    60.00
     polarization
    50.00
     Pol
    49.75
    Pol
    46.75
     pol
    44.75
    pol
    43.75
    極
    42.75
     POL
    42.50
    Activations Density 0.058%

    No Known Activations