© 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. 14450
    Prev
    Next
    INDEX
    Explanations

    Chinese words

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

    No Comments

    Negative Logits
     Hutchinson
    -19.63
     Robbie
    -17.88
     maid
    -17.63
     Elliot
    -17.38
    Rotor
    -17.25
     Curtis
    -16.88
     Pruitt
    -16.25
    úc
    -16.13
    rott
    -16.13
     Roth
    -16.00
    POSITIVE LOGITS
     deer
    19.13
     Deer
    17.88
    丈
    16.75
    hin
    15.75
    银河
    15.56
    enumer
    15.50
    钉
    15.44
    粱
    15.44
    leep
    15.25
    �
    15.13
    Activations Density 1.225%

    No Known Activations