© 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. 2427
    Prev
    Next
    INDEX
    Explanations

    say "回"

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

    No Comments

    Negative Logits
     proposition
    -16.00
     comm
    -15.94
     propositions
    -15.31
    _Rel
    -15.13
    erp
    -15.06
     annihil
    -14.00
    alach
    -13.94
     AuthService
    -13.88
    .cert
    -13.88
    .tt
    -13.81
    POSITIVE LOGITS
    回
    77.00
    (ret
    63.50
     ret
    61.50
    Ret
    59.00
    ret
    58.75
     Ret
    58.00
    .ret
    57.25
    -ret
    57.00
    	ret
    54.50
    _ret
    54.25
    Activations Density 0.120%

    No Known Activations