© 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. 2312
    Prev
    Next
    INDEX
    Explanations

    say "par" words

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

    No Comments

    Negative Logits
     ret
    -19.38
    resident
    -19.00
     mill
    -18.00
    (ret
    -18.00
     res
    -18.00
    resolve
    -17.25
    	ret
    -16.50
    $ret
    -16.38
     Mill
    -16.38
    ret
    -16.38
    POSITIVE LOGITS
     metaph
    32.75
    Eth
    24.38
    乙
    23.63
    ETH
    23.38
    eth
    22.38
     eth
    22.25
    refs
    21.63
     Eth
    20.88
     metaphor
    20.25
    beth
    20.25
    Activations Density 0.041%

    No Known Activations